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

    Neuronpedia

    INDEX
    Explanations

    serve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scientific
    -0.07
    blick
    -0.07
    沥青
    -0.07
     blond
    -0.07
    _steps
    -0.07
    漫画
    -0.07
     Assess
    -0.07
     KB
    -0.07
    _STAT
    -0.06
    nowledge
    -0.06
    POSITIVE LOGITS
    (fs
    0.07
    ']}
    0.07
    #plt
    0.07
    }elseif
    0.07
    .fi
    0.07
    ')}
    0.07
    脸上
    0.07
     metall
    0.07
    (lr
    0.06
     jr
    0.06
    Act Density 0.012%

    No Known Activations