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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     får
    -0.07
    079
    -0.07
    708
    -0.06
    /www
    -0.06
     Yeni
    -0.06
     foyer
    -0.06
    Fizz
    -0.06
    .generic
    -0.06
     nhiệm
    -0.06
     контроль
    -0.06
    POSITIVE LOGITS
    дап
    0.07
    osphate
    0.07
    वत
    0.07
    paint
    0.06
    acock
    0.06
     Sampler
    0.06
    付け
    0.06
    Samples
    0.06
    employment
    0.06
    त
    0.06
    Act Density 0.026%

    No Known Activations