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
    .copyWith
    -0.08
    placed
    -0.07
    otypes
    -0.07
    овах
    -0.07
    ker
    -0.07
    odel
    -0.06
    _storage
    -0.06
    ौं
    -0.06
    olta
    -0.06
    죽
    -0.06
    POSITIVE LOGITS
     Jab
    0.07
     instantly
    0.07
     Fram
    0.06
     enable
    0.06
     wishing
    0.06
     progression
    0.06
     ESPN
    0.06
     grosse
    0.06
     zajist
    0.06
     Lit
    0.06
    Act Density 0.080%

    No Known Activations