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

    Neuronpedia

    INDEX
    Explanations

    code, names, information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UrlResolution
    -0.65
     Theſe
    -0.60
     insuffisamment
    -0.60
     ainfi
    -0.59
    Stopping
    -0.58
     ?>>
    -0.57
    Stro
    -0.57
     whereof
    -0.57
    UnitTesting
    -0.56
     becauſe
    -0.56
    POSITIVE LOGITS
     cross
    0.56
     breed
    0.52
    GEBURTSDATUM
    0.52
     swell
    0.50
     cripple
    0.49
    :✨
    0.49
     sweep
    0.48
     loom
    0.48
     shatter
    0.47
     thicken
    0.47
    Act Density 0.000%

    No Known Activations