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

    Neuronpedia

    INDEX
    Explanations

    implant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    寥
    -0.07
    .functions
    -0.07
    chas
    -0.07
    度
    -0.07
    adies
    -0.07
    一向
    -0.07
     fig
    -0.06
    .fig
    -0.06
     statutes
    -0.06
    strument
    -0.06
    POSITIVE LOGITS
     Paperback
    0.07
    /%
    0.07
    𝗘
    0.07
    /storage
    0.07
     ticker
    0.07
    tablet
    0.07
    _EQ
    0.07
    很深
    0.07
    سار
    0.06
    เก
    0.06
    Act Density 0.002%

    No Known Activations