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

    Neuronpedia

    INDEX
    Explanations

    website rankings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bac
    -0.07
     domic
    -0.07
    将其
    -0.07
    炎
    -0.07
    ubernetes
    -0.07
    igure
    -0.06
    Submitting
    -0.06
    郝
    -0.06
     prolific
    -0.06
     comma
    -0.06
    POSITIVE LOGITS
     Lith
    0.07
     המע
    0.07
    гран
    0.07
     unk
    0.07
    .Utility
    0.07
    CHAN
    0.06
    CAN
    0.06
    ЛЬ
    0.06
    -display
    0.06
    _contains
    0.06
    Act Density 0.002%

    No Known Activations