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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    masters
    -0.08
    Bus
    -0.07
     blush
    -0.07
     Sand
    -0.07
    SDK
    -0.07
     leuk
    -0.07
     ام
    -0.07
    measure
    -0.07
     methods
    -0.06
    โก
    -0.06
    POSITIVE LOGITS
    iž
    0.07
    ической
    0.06
     Datensch
    0.06
    さま
    0.06
    ぇ
    0.06
    628
    0.06
     비
    0.06
    ch
    0.06
     همیشه
    0.06
    prix
    0.06
    Act Density 0.019%

    No Known Activations