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

    Neuronpedia

    INDEX
    Explanations

    scientific numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kültür
    -0.07
     grilled
    -0.07
     UIControl
    -0.07
    perse
    -0.07
     light
    -0.06
     nig
    -0.06
     Stunning
    -0.06
    绰
    -0.06
    oueur
    -0.06
     الثنائية
    -0.06
    POSITIVE LOGITS
    indh
    0.07
    <translation
    0.07
    ucid
    0.07
     опыт
    0.07
    宝藏
    0.07
    _LOW
    0.07
    series
    0.06
     batching
    0.06
    _ylim
    0.06
    elta
    0.06
    Act Density 0.047%

    No Known Activations