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

    Neuronpedia

    INDEX
    Explanations

    interrogative phrases and questions related to time and presence

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

    question marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.52
    CppMethod
    -0.48
    criminator
    -0.48
     >=",
    -0.47
     <=",
    -0.42
    RefNanny
    -0.40
     lagar
    -0.40
     ModelRenderer
    -0.39
    elemField
    -0.39
    NamedQueries
    -0.39
    POSITIVE LOGITS
    ?
    0.50
     متعلقه
    0.47
    ()?
    0.46
    ？
    0.46
    ...?
    0.45
    …?
    0.45
    ?):
    0.45
    ?”
    0.45
    ?..
    0.44
    ?).
    0.43
    Act Density 0.110%

    No Known Activations