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
     Aydın
    -0.06
    Executive
    -0.06
    _dummy
    -0.06
    anos
    -0.06
     fwd
    -0.06
    -compatible
    -0.06
    AlmostEqual
    -0.06
    	AM
    -0.06
    Philip
    -0.06
    ibar
    -0.06
    POSITIVE LOGITS
     hart
    0.07
    zahl
    0.07
    ensen
    0.06
     ----------------------------------------------------------------------------↵
    0.06
    丁
    0.06
    _opt
    0.06
     Shard
    0.06
    مم
    0.06
    471
    0.06
    fal
    0.06
    Act Density 0.000%

    No Known Activations