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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    녁
    -0.07
    GING
    -0.07
    üğü
    -0.07
    𫘬
    -0.07
    ｫ
    -0.07
    _snapshot
    -0.07
    .MapFrom
    -0.07
    atrigesimal
    -0.06
    _scr
    -0.06
    ﯫ
    -0.06
    POSITIVE LOGITS
     reactor
    0.08
    destroy
    0.07
     mage
    0.07
     voiced
    0.07
    MG
    0.07
     Ey
    0.07
     assass
    0.06
    ),$
    0.06
    反應
    0.06
     vent
    0.06
    Act Density 0.080%

    No Known Activations