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

    Neuronpedia

    INDEX
    Explanations

    assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    羞
    -0.07
    .youtube
    -0.07
    .DisplayName
    -0.06
     offending
    -0.06
     pronounce
    -0.06
    (json
    -0.06
     lect
    -0.06
     yellow
    -0.06
    yellow
    -0.06
    解决问题
    -0.06
    POSITIVE LOGITS
    ﻫ
    0.08
    "].
    0.08
    ₤
    0.07
    ﺽ
    0.07
    NSUserDefaults
    0.07
     //////////////////////////////////////////////////////////////////////
    0.07
    .pnl
    0.07
    Enumerable
    0.07
    рин
    0.07
    𝓫
    0.07
    Act Density 0.020%

    No Known Activations