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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _inp
    -0.07
     Timeout
    -0.07
    Jos
    -0.06
    lığa
    -0.06
     Registry
    -0.06
    Decrypt
    -0.06
     каз
    -0.06
     confusing
    -0.06
     Jos
    -0.06
     languages
    -0.06
    POSITIVE LOGITS
     関連
    0.07
    рач
    0.07
    _lower
    0.07
    .Firebase
    0.07
    -family
    0.06
    χή
    0.06
    ении
    0.06
     Мі
    0.06
    しい
    0.06
     Externí
    0.06
    Act Density 0.019%

    No Known Activations