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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Enumerator
    -0.07
    妻
    -0.07
    erequisite
    -0.07
     notation
    -0.07
    _MISS
    -0.07
    -series
    -0.06
     ناب
    -0.06
     六
    -0.06
    _WIDGET
    -0.06
    _learn
    -0.06
    POSITIVE LOGITS
    (fin
    0.06
    :NSLayout
    0.06
     富
    0.06
     \↵↵
    0.06
    ]:
↵
    0.06
     apro
    0.06
     thưởng
    0.05
    )))↵↵↵
    0.05
    slope
    0.05
    File
    0.05
    Act Density 0.015%

    No Known Activations