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

    Neuronpedia

    INDEX
    Explanations

    Code/Configuration Files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -box
    -0.08
     kicking
    -0.07
     stations
    -0.07
    x
    -0.07
    _keyword
    -0.07
     pixels
    -0.07
    习
    -0.07
     bad
    -0.07
     top
    -0.07
    怕
    -0.07
    POSITIVE LOGITS
    0.08
    0.08
     Dur
    0.08
    ูไ
    0.07
     sürdür
    0.07
    (conf
    0.07
    0.07
     Gran
    0.07
    .MULT
    0.07
     �
    0.07
    Act Density 0.043%

    No Known Activations