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

    Neuronpedia

    INDEX
    Explanations

    ning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zdarma
    -0.07
    ircon
    -0.07
    ırak
    -0.07
    케
    -0.06
     zas
    -0.06
     Stap
    -0.06
     говорить
    -0.06
     ris
    -0.06
    Born
    -0.06
    ㄷ
    -0.06
    POSITIVE LOGITS
     holiday
    0.06
    nofollow
    0.06
    /use
    0.06
    aviors
    0.06
    .playlist
    0.06
    _short
    0.06
    dx
    0.06
    ensual
    0.06
     lawn
    0.06
    _minimum
    0.06
    Act Density 0.000%

    No Known Activations