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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .txt
    -0.08
     Ksi
    -0.07
     europ
    -0.07
    iveau
    -0.07
    شع
    -0.07
    露出
    -0.07
     Refugee
    -0.07
    usuarios
    -0.06
    ￨
    -0.06
    ערוץ
    -0.06
    POSITIVE LOGITS
    נן
    0.08
     �
    0.07
    !!!↵
    0.07
    ogen
    0.07
     relax
    0.06
    廠
    0.06
     Problems
    0.06
    уют
    0.06
    均衡
    0.06
     QtGui
    0.06
    Act Density 0.004%

    No Known Activations