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

    Neuronpedia

    INDEX
    Explanations

    Crime and sabotage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ")
    -0.07
    ek
    -0.06
     Phillip
    -0.06
     NUM
    -0.06
    _UC
    -0.06
    .Gson
    -0.06
    �
    -0.06
     Status
    -0.06
     BEGIN
    -0.06
    )],
    -0.06
    POSITIVE LOGITS
    Otherwise
    0.06
    _taxonomy
    0.06
    ionální
    0.06
    прав
    0.06
    符
    0.06
    _locale
    0.06
     anonymous
    0.06
    projectId
    0.06
    antd
    0.06
     качества
    0.06
    Act Density 0.183%

    No Known Activations