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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    061
    -0.08
    SER
    -0.07
    _extractor
    -0.07
     Mam
    -0.07
    られ
    -0.07
     dil
    -0.06
    note
    -0.06
     mam
    -0.06
     coil
    -0.06
    _FINAL
    -0.06
    POSITIVE LOGITS
    	email
    0.07
    刘
    0.07
    類
    0.06
    (QtCore
    0.06
     compassionate
    0.06
     اساسی
    0.06
     Portugal
    0.06
    Dept
    0.06
     цим
    0.06
     displacement
    0.06
    Act Density 0.002%

    No Known Activations