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

    Neuronpedia

    INDEX
    Explanations

    14

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smoothed
    -0.07
     divisor
    -0.07
     evening
    -0.06
     отмеч
    -0.06
    .matches
    -0.06
     afternoon
    -0.06
     عص
    -0.06
     Zero
    -0.06
     براي
    -0.06
     předch
    -0.06
    POSITIVE LOGITS
    لي
    0.07
    icit
    0.07
    ใ
    0.07
    /plugins
    0.06
    .FILE
    0.06
     Connecting
    0.06
    indexPath
    0.06
    ction
    0.06
    singleton
    0.06
    Turkey
    0.06
    Act Density 0.002%

    No Known Activations