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

    Neuronpedia

    INDEX
    Explanations

    violence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绝大部分
    -0.07
     FLASH
    -0.07
    לבן
    -0.07
     archives
    -0.06
    高端
    -0.06
     mirrored
    -0.06
     GRAPH
    -0.06
    /,
    -0.06
    _fifo
    -0.06
     harming
    -0.06
    POSITIVE LOGITS
    ｐ
    0.07
    ᒋ
    0.07
    .transactions
    0.07
    ربح
    0.06
     nhé
    0.06
    operators
    0.06
     ucwords
    0.06
     stringent
    0.06
    species
    0.06
    .getX
    0.06
    Act Density 0.009%

    No Known Activations