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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     batteries
    -0.07
     borrowed
    -0.06
     coordinated
    -0.06
    ilebilir
    -0.06
     RadioButton
    -0.06
    城市
    -0.06
     Ny
    -0.06
    fir
    -0.06
     관
    -0.06
     البي
    -0.06
    POSITIVE LOGITS
    ��
    0.08
     символ
    0.07
    orsche
    0.06
    ROTO
    0.06
    NOWLED
    0.06
     unix
    0.06
     }},↵
    0.06
    ValueGenerationStrategy
    0.06
    MF
    0.06
    -looking
    0.06
    Act Density 0.002%

    No Known Activations