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

    Neuronpedia

    INDEX
    Explanations

    В

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    цем
    -0.08
     breeding
    -0.07
    指
    -0.07
    &_
    -0.06
     falta
    -0.06
    iqu
    -0.06
    Book
    -0.06
    vou
    -0.06
    ored
    -0.06
    .cod
    -0.06
    POSITIVE LOGITS
    .Config
    0.06
     Distrib
    0.06
     Âu
    0.06
     dodge
    0.06
     PANEL
    0.06
    .Xna
    0.06
     volcan
    0.06
     граждан
    0.06
    fuck
    0.06
    /".$
    0.06
    Act Density 0.075%

    No Known Activations