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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to technical specifications and programming concepts

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

    Follows a noun, then "is/are"

    np_acts-logits-general · gemini-2.0-flash

    concepts and their descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étant
    -0.68
    étant
    -0.58
     esternos
    -0.54
    ActionCreators
    -0.52
    เอง
    -0.52
    ayant
    -0.52
     qualités
    -0.51
     réguli
    -0.51
     infatti
    -0.50
     также
    -0.50
    POSITIVE LOGITS
    IVEREF
    0.74
     cares
    0.57
    annia
    0.55
     deals
    0.55
     entails
    0.54
     got
    0.54
    }\{
    0.54
     really
    0.53
     所
    0.52
     بلکه
    0.52
    Act Density 0.415%

    No Known Activations