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
    _neurons
    -0.07
    vang
    -0.07
     Sandra
    -0.06
    정을
    -0.06
     Atlantic
    -0.06
     smelled
    -0.06
    可能
    -0.06
     sufficiently
    -0.06
    .mas
    -0.06
    (single
    -0.06
    POSITIVE LOGITS
     rencontrer
    0.07
     Deleted
    0.07
    endforeach
    0.06
    .AllowGet
    0.06
    電話
    0.06
    extAlignment
    0.06
     wxT
    0.06
    VERTISEMENT
    0.06
    ENSION
    0.06
     GCC
    0.06
    Act Density 0.047%

    No Known Activations