Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms related to mechanical components and assemblies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following prepositions like "with", "to", "of", etc

    np_acts-logits-general · gemini-2.0-flash

    mechanical components and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Réponses
    -0.63
     >=",
    -0.62
    CloseOperation
    -0.61
    makeConstraints
    -0.54
     CreateTagHelper
    -0.54
     BoxFit
    -0.54
     vraie
    -0.53
     gynhyrchwyd
    -0.53
     dingen
    -0.52
     atacado
    -0.50
    POSITIVE LOGITS
     supporting
    0.69
     housing
    0.67
     support
    0.63
     member
    0.60
    WriteBarrier
    0.58
     upper
    0.57
    supporting
    0.57
     plurality
    0.54
    ſelf
    0.54
     partition
    0.54
    Act Density 1.236%

    No Known Activations