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

    Neuronpedia

    INDEX
    Explanations

    mass

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    хьтан
    -0.83
     myſelf
    -0.83
     Efq
    -0.82
     auffi
    -0.73
    ſelf
    -0.69
     Jefus
    -0.69
    esserung
    -0.68
    AlterField
    -0.67
    MLLoader
    -0.67
     himſelf
    -0.65
    POSITIVE LOGITS
     ch
    0.46
    TagHelpers
    0.45
    :✨
    0.42
    alini
    0.42
     sp
    0.40
    pfe
    0.38
    MNA
    0.37
    chon
    0.37
     window
    0.37
    新浪
    0.36
    Act Density 0.002%

    No Known Activations