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

    Neuronpedia

    INDEX
    Explanations

    suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    perience
    -0.07
    180
    -0.07
    electronics
    -0.07
     през
    -0.07
     disponible
    -0.07
     начале
    -0.07
     advance
    -0.07
    _month
    -0.07
    ieran
    -0.07
    _est
    -0.07
    POSITIVE LOGITS
     suffix
    0.13
    uffix
    0.12
    _suffix
    0.11
    suffix
    0.10
    Suffix
    0.10
    _SUFFIX
    0.09
    (suffix
    0.09
    UFFIX
    0.08
     Fuji
    0.07
     때
    0.07
    Act Density 0.002%

    No Known Activations