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
    (Time
    -0.07
     王
    -0.06
     će
    -0.06
     �
    -0.06
     ▼
    -0.06
     интерес
    -0.06
     Republican
    -0.06
     Vietnam
    -0.06
     bề
    -0.06
     moet
    -0.06
    POSITIVE LOGITS
    .ib
    0.07
    기는
    0.07
    hydro
    0.07
     гориз
    0.06
     зем
    0.06
     subscribing
    0.06
     HB
    0.06
    }());↵
    0.06
    .crm
    0.06
    “So
    0.06
    Act Density 0.035%

    No Known Activations