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

    Neuronpedia

    INDEX
    Explanations

    ");

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    確
    -0.08
    /docs
    -0.07
     Trom
    -0.07
    榉
    -0.07
    医科大学
    -0.07
    ຄ
    -0.07
    .Stream
    -0.07
    立志
    -0.07
    Non
    -0.06
    破裂
    -0.06
    POSITIVE LOGITS
     gent
    0.08
    groupon
    0.08
     apology
    0.07
    蹐
    0.07
    Whole
    0.07
    unately
    0.07
    руг
    0.07
    every
    0.06
     POSIX
    0.06
    /sn
    0.06
    Act Density 0.015%

    No Known Activations