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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gösteren
    -0.07
     loft
    -0.06
     nevě
    -0.06
    .choice
    -0.06
    -D
    -0.06
     prenatal
    -0.06
    Will
    -0.06
    .XRLabel
    -0.06
     ゝ
    -0.06
    HRESULT
    -0.06
    POSITIVE LOGITS
    validate
    0.07
    。しかし
    0.07
    'ят
    0.07
     ensl
    0.06
    ्मक
    0.06
    wald
    0.06
    ’ят
    0.06
    収
    0.06
     socio
    0.06
    .shortcuts
    0.06
    Act Density 0.033%

    No Known Activations