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

    Neuronpedia

    INDEX
    Explanations

    questions and discussions related to equality and societal issues

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

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.68
     Numerade
    -0.57
     ProtoMessage
    -0.56
    OGND
    -0.56
     GenerationType
    -0.56
    IndentedString
    -0.56
    principalColumn
    -0.53
    chengladbach
    -0.52
    findpost
    -0.49
     Италијани
    -0.49
    POSITIVE LOGITS
    それとも
    0.56
    addContainerGap
    0.53
    VersionUID
    0.49
    ?
    0.47
    会不会
    0.46
    果た
    0.46
    ...?
    0.45
    ...?"
    0.45
    ?$
    0.44
    SupportActionBar
    0.43
    Act Density 0.059%

    No Known Activations