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

    Neuronpedia

    INDEX
    Explanations

    risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rokken
    -0.52
    anskje
    -0.52
     it
    -0.50
     the
    -0.50
     scope
    -0.48
     that
    -0.47
     life
    -0.47
     offense
    -0.46
     Go
    -0.45
     jatuh
    -0.45
    POSITIVE LOGITS
    tvguidetime
    0.83
    脚注の使い方
    0.69
    TintMode
    0.67
    tagHelperRunner
    0.66
    neurial
    0.64
     genoux
    0.63
     oreilles
    0.60
    telser
    0.60
    %/
    0.59
    舺
    0.59
    Act Density 0.312%

    No Known Activations