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

    Neuronpedia

    INDEX
    Explanations

    such

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()){
    -0.08
     Κου
    -0.07
     Uganda
    -0.07
     Fridays
    -0.06
    629
    -0.06
    ','-
    -0.06
     bleak
    -0.06
    treeview
    -0.06
     qty
    -0.06
    kova
    -0.06
    POSITIVE LOGITS
     insan
    0.07
    LL
    0.06
     hookup
    0.06
    らしい
    0.06
     metabol
    0.06
    ęd
    0.06
    odor
    0.06
    Tur
    0.06
    _heading
    0.06
    illo
    0.06
    Act Density 0.185%

    No Known Activations