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
     essen
    -0.08
    .Utils
    -0.07
     Bonus
    -0.07
    pytest
    -0.07
     vbox
    -0.07
     SENT
    -0.07
     SEND
    -0.07
     roc
    -0.07
    aeda
    -0.06
    Generic
    -0.06
    POSITIVE LOGITS
    acyj
    0.08
     giriş
    0.07
     国家
    0.06
    FormsModule
    0.06
     shaping
    0.06
     ἐ
    0.06
    itimate
    0.06
    -duty
    0.06
     lowercase
    0.06
     hardcoded
    0.06
    Act Density 0.231%

    No Known Activations