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

    Neuronpedia

    INDEX
    Explanations

    jobs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UITableViewCell
    -0.07
     hosp
    -0.07
    庙
    -0.07
    glyph
    -0.07
     upbeat
    -0.06
    violent
    -0.06
    中秋
    -0.06
     pitches
    -0.06
    licts
    -0.06
    קפה
    -0.06
    POSITIVE LOGITS
     continuously
    0.08
    室外
    0.07
     Mull
    0.07
     uLocal
    0.07
     phosphate
    0.07
    不允许
    0.07
     broadcast
    0.06
    体力
    0.06
     regardless
    0.06
    _confirm
    0.06
    Act Density 0.002%

    No Known Activations