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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Slug
    -0.08
     משחק
    -0.07
    扉
    -0.07
     Archived
    -0.07
     SOC
    -0.07
    _permissions
    -0.07
    笑
    -0.06
    锹
    -0.06
    栎
    -0.06
    唉
    -0.06
    POSITIVE LOGITS
     ferm
    0.07
    Glass
    0.07
     FF
    0.07
    ира
    0.07
    يدة
    0.06
    _render
    0.06
    strap
    0.06
     locale
    0.06
    ategorical
    0.06
    不是
    0.06
    Act Density 0.003%

    No Known Activations