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

    Neuronpedia

    INDEX
    Explanations

    April

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rabilir
    -0.08
     nonzero
    -0.07
     Belt
    -0.07
     belt
    -0.07
    ini
    -0.07
     Не
    -0.07
    Fre
    -0.06
    ilere
    -0.06
    eldig
    -0.06
    нт
    -0.06
    POSITIVE LOGITS
     زیب
    0.07
     Sep
    0.07
    .generated
    0.06
     yem
    0.06
     advised
    0.06
    _cats
    0.06
     motivating
    0.06
     provid
    0.06
    -shift
    0.06
     朝
    0.06
    Act Density 0.025%

    No Known Activations