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

    Neuronpedia

    INDEX
    Explanations

    htmlspecialchars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     empty
    -0.08
    ٥
    -0.07
    يز
    -0.07
     Associ
    -0.06
     bloom
    -0.06
    GetY
    -0.06
     slower
    -0.06
    败
    -0.06
    Empty
    -0.06
     engine
    -0.06
    POSITIVE LOGITS
     acquaint
    0.07
     수상
    0.07
    .setAlignment
    0.06
    (Packet
    0.06
     необ
    0.06
     *----------------------------------------------------------------
    0.06
    .answers
    0.06
     Peygamber
    0.06
     Mic
    0.06
    .Suppress
    0.06
    Act Density 0.009%

    No Known Activations