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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating location and context

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

    "on the" followed by a reason/explanation

    np_acts-logits-general · gemini-2.0-flash

    on the ground, on account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thereunder
    -0.61
     AssemblyProduct
    -0.60
     intStringLen
    -0.59
     '\\;'
    -0.57
     Normdatei
    -0.56
     NavController
    -0.56
    AsUp
    -0.56
    UnknownFieldSet
    -0.55
    Personensuche
    -0.54
    NamedQueries
    -0.54
    POSITIVE LOGITS
     account
    0.75
     grounds
    0.70
     behalf
    0.62
     instructions
    0.61
    account
    0.59
     completion
    0.57
     basis
    0.54
    instructions
    0.54
     instruction
    0.54
     strength
    0.53
    Act Density 0.250%

    No Known Activations