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

    Neuronpedia

    INDEX
    Explanations

    Matrix organizational structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roupa
    -0.08
     cosplay
    -0.08
     Portugu
    -0.07
     nche
    -0.07
     Mol
    -0.07
     zuverläss
    -0.07
    铜
    -0.07
    702
    -0.07
     Pública
    -0.07
     cif
    -0.07
    POSITIVE LOGITS
     restruct
    0.09
    ях
    0.08
    予
    0.08
     undue
    0.07
     maze
    0.07
    Sorry
    0.07
    以后
    0.07
     infusion
    0.07
    treated
    0.07
    _SCALE
    0.07
    Act Density 0.003%

    No Known Activations