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

    Neuronpedia

    INDEX
    Explanations

    bic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     method
    -0.90
     Seen
    -0.80
    method
    -0.73
     seen
    -0.72
    Seen
    -0.71
     Seeing
    -0.69
    seen
    -0.67
     Method
    -0.66
     METHOD
    -0.65
     método
    -0.63
    POSITIVE LOGITS
     дописавши
    0.76
    TestingModule
    0.70
     Spisak
    0.67
     '\\;'
    0.66
     pngtree
    0.65
    ThemeOverlay
    0.64
    unhofer
    0.63
    SdkVersion
    0.62
     nominating
    0.60
     חיצוניים
    0.59
    Act Density 0.131%

    No Known Activations