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

    Neuronpedia

    INDEX
    Explanations

    welcome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posi
    -0.07
    621
    -0.07
     parameters
    -0.06
     состояния
    -0.06
    ō
    -0.06
     SSD
    -0.06
     models
    -0.06
     zcela
    -0.06
     vocalist
    -0.06
     writes
    -0.06
    POSITIVE LOGITS
    錯
    0.07
     цер
    0.07
     Normal
    0.06
    :message
    0.06
     Alpha
    0.06
     ontvang
    0.06
    ذه
    0.06
     Eagle
    0.06
    _TMP
    0.06
     MAY
    0.06
    Act Density 0.001%

    No Known Activations