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

    Neuronpedia

    INDEX
    Explanations

    District

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     owed
    -0.07
    	RTE
    -0.07
    .f
    -0.07
    "Oh
    -0.07
     труда
    -0.06
    _M
    -0.06
     jerk
    -0.06
    .embedding
    -0.06
    幕
    -0.06
     halfway
    -0.06
    POSITIVE LOGITS
    ้ก
    0.07
    valor
    0.07
     cured
    0.06
    Options
    0.06
    value
    0.06
     collected
    0.06
     sheds
    0.06
    الش
    0.06
    シャ
    0.06
    ="'.
    0.06
    Act Density 0.001%

    No Known Activations