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

    Neuronpedia

    INDEX
    Explanations

    code snippets/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    多少
    -0.07
    _ips
    -0.07
     ندار
    -0.07
     slid
    -0.06
     pharmacy
    -0.06
     SID
    -0.06
    自由
    -0.06
     Ct
    -0.06
     )}↵↵
    -0.06
     Shades
    -0.06
    POSITIVE LOGITS
    时候
    0.07
    руг
    0.07
     sunrise
    0.07
     rather
    0.06
    аніз
    0.06
     passive
    0.06
     filling
    0.06
    yní
    0.06
    ثار
    0.06
     ere
    0.06
    Act Density 0.000%

    No Known Activations