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

    Neuronpedia

    INDEX
    Explanations

    voice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    щен
    -0.08
     traveler
    -0.08
    倡
    -0.08
     upp
    -0.07
     communion
    -0.07
    .um
    -0.07
    ஸ
    -0.07
    ----------↵↵
    -0.07
    -security
    -0.07
     Vaccine
    -0.06
    POSITIVE LOGITS
    办案
    0.07
    💁
    0.07
     당시
    0.07
    南山
    0.07
     kind
    0.06
    𬱖
    0.06
    救治
    0.06
     steady
    0.06
     ре
    0.06
    ny
    0.06
    Act Density 0.058%

    No Known Activations