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

    Neuronpedia

    INDEX
    Explanations

    yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WithEvents
    -0.07
    .Children
    -0.07
    .fake
    -0.06
     idol
    -0.06
     Top
    -0.06
     whilst
    -0.06
     substance
    -0.06
    .multiply
    -0.06
     doorway
    -0.06
     reversed
    -0.06
    POSITIVE LOGITS
    ЕН
    0.07
    من
    0.06
     возв
    0.06
    ても
    0.06
    انون
    0.06
    инув
    0.06
    าจะ
    0.06
     thẻ
    0.06
    رت
    0.06
    ElapsedTime
    0.06
    Act Density 0.000%

    No Known Activations