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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases related to inquiries or requests for information

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

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.78
     surla
    -0.62
    styleType
    -0.60
     kohdetta
    -0.60
    TypedDataSet
    -0.60
     Roskov
    -0.60
     OMITBAD
    -0.58
    hoeddwyd
    -0.58
    Espèce
    -0.57
     contextLoads
    -0.57
    POSITIVE LOGITS
    </strong>
    0.37
     interested
    0.36
    any
    0.35
     assistance
    0.35
    ęd
    0.34
     concerned
    0.34
     concerns
    0.34
     czu
    0.34
     questions
    0.32
     lost
    0.32
    Act Density 0.015%

    No Known Activations