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

    Neuronpedia

    INDEX
    Explanations

    General English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عم
    -0.07
    цу
    -0.06
    	ar
    -0.06
    eming
    -0.06
    ocrin
    -0.06
     mec
    -0.06
     pulls
    -0.06
     честь
    -0.06
    mnop
    -0.06
    ?a
    -0.06
    POSITIVE LOGITS
    _toggle
    0.07
    égorie
    0.07
    atitude
    0.06
    頁
    0.06
    Lights
    0.06
    Dataset
    0.06
    ierre
    0.06
    dart
    0.06
    ')}}"></
    0.06
    translations
    0.06
    Act Density 0.003%

    No Known Activations