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

    Neuronpedia

    INDEX
    Explanations

    license

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Particip
    -0.07
     cycle
    -0.06
     minimized
    -0.06
     하는
    -0.06
     Girl
    -0.06
    egative
    -0.06
    Flying
    -0.06
    ossip
    -0.06
     Lớp
    -0.06
     pieces
    -0.06
    POSITIVE LOGITS
     topl
    0.07
     собира
    0.07
     Hier
    0.06
    toContain
    0.06
    _ast
    0.06
    ynos
    0.06
    "use
    0.06
    озвращ
    0.06
     Franti
    0.06
    DialogContent
    0.06
    Act Density 0.002%

    No Known Activations