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
    spect
    -0.08
    脯
    -0.07
    圃
    -0.07
    .bind
    -0.06
     weary
    -0.06
    呼
    -0.06
    斑斓
    -0.06
    标识
    -0.06
    LOG
    -0.06
     규정
    -0.06
    POSITIVE LOGITS
    (payment
    0.07
     nhiêu
    0.07
    女孩
    0.07
     $('#'
    0.07
     centers
    0.07
     serum
    0.07
    �
    0.07
     ','.
    0.06
     novelty
    0.06
     ')[
    0.06
    Act Density 0.003%

    No Known Activations