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

    Neuronpedia

    INDEX
    Explanations

    Medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     account
    -0.07
    됀
    -0.07
    蛩
    -0.07
    汇总
    -0.06
     destined
    -0.06
     Shared
    -0.06
     defends
    -0.06
     Schultz
    -0.06
    .Loader
    -0.06
     lizard
    -0.06
    POSITIVE LOGITS
    Implicit
    0.08
    淡淡的
    0.08
    `)↵
    0.08
     preg
    0.07
    ↘
    0.07
     estable
    0.07
    ત
    0.07
     muit
    0.07
    _elem
    0.07
    宛
    0.07
    Act Density 0.073%

    No Known Activations