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

    Neuronpedia

    INDEX
    Explanations

    privately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     causal
    -0.06
     تحقیق
    -0.06
     PlayerPrefs
    -0.06
     kB
    -0.06
    Separator
    -0.06
    896
    -0.06
     bueno
    -0.06
    謝
    -0.06
    termination
    -0.06
    Statistics
    -0.06
    POSITIVE LOGITS
     når
    0.07
     isc
    0.07
    (nr
    0.06
     zaten
    0.06
    _hand
    0.06
     pled
    0.06
     Bh
    0.06
    �
    0.06
    abeth
    0.06
    (PATH
    0.06
    Act Density 0.003%

    No Known Activations