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

    Neuronpedia

    INDEX
    Explanations

    robberies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     支
    -0.07
    وا
    -0.07
    زه
    -0.07
     및
    -0.06
    ští
    -0.06
    GenerationStrategy
    -0.06
     HWND
    -0.06
    _buffers
    -0.06
    _LOOKUP
    -0.06
     NL
    -0.06
    POSITIVE LOGITS
     Winnipeg
    0.06
     seksi
    0.06
     chances
    0.06
     Colleg
    0.06
     saber
    0.06
     autom
    0.06
     GH
    0.06
     freaking
    0.06
     pollution
    0.06
     incapable
    0.06
    Act Density 0.040%

    No Known Activations