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

    Neuronpedia

    INDEX
    Explanations

    extern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    74
    -0.07
     Ninh
    -0.07
     utterly
    -0.07
     düzenlenen
    -0.07
     Killer
    -0.07
     الأمريكي
    -0.06
     refactor
    -0.06
    ита
    -0.06
     reused
    -0.06
    ΙΟΥ
    -0.06
    POSITIVE LOGITS
     NSLog
    0.07
    earned
    0.06
     matplotlib
    0.06
     αρχ
    0.06
     зг
    0.06
     incontr
    0.06
    (for
    0.06
    .fromFunction
    0.06
     horizon
    0.06
     sofa
    0.06
    Act Density 0.001%

    No Known Activations