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

    Neuronpedia

    INDEX
    Explanations

    concerns related to safety and health risks for individuals and communities

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

    safety and well-being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iastes
    -0.56
     autorytatywna
    -0.52
     wireType
    -0.45
    SerializedName
    -0.45
     برانيه
    -0.45
    BibitemShut
    -0.44
     ErrIntOverflow
    -0.44
    SerializedSize
    -0.43
    %"),
    -0.43
    hilangan
    -0.43
    POSITIVE LOGITS
     employees
    0.65
     visitors
    0.64
     workers
    0.62
    innocent
    0.61
     innocent
    0.61
     safety
    0.59
    Safety
    0.58
     proteger
    0.57
     everyone
    0.56
     passengers
    0.56
    Act Density 0.021%

    No Known Activations