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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ولوژی
    -0.07
    cock
    -0.07
    otional
    -0.06
     disappears
    -0.06
    /bar
    -0.06
    shirt
    -0.06
    دری
    -0.06
    _closure
    -0.06
     assemble
    -0.06
    ameleon
    -0.06
    POSITIVE LOGITS
    骑
    0.07
     mux
    0.06
     Qty
    0.06
    +='<
    0.06
     PAN
    0.06
     والت
    0.06
     très
    0.06
    Jak
    0.06
    catid
    0.06
    _fifo
    0.06
    Act Density 0.082%

    No Known Activations