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

    Neuronpedia

    INDEX
    Explanations

    Publication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regimen
    -0.08
    尸体
    -0.07
     Nhà
    -0.07
     Cher
    -0.07
    üstü
    -0.06
    REP
    -0.06
     ')↵↵
    -0.06
     זו
    -0.06
    _bp
    -0.06
    "));
↵
↵
    -0.06
    POSITIVE LOGITS
     gusto
    0.08
     streamed
    0.08
     scrolls
    0.07
    uccess
    0.07
    .Permission
    0.07
    -power
    0.07
    ปาก
    0.07
     namespace
    0.07
     toolbar
    0.07
     altura
    0.07
    Act Density 0.001%

    No Known Activations