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

    Neuronpedia

    INDEX
    Explanations

    structural markers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fmat
    1.03
     tendances
    1.01
    ла
    1.01
     principales
    0.96
     alarg
    0.94
     calent
    0.93
     tiver
    0.92
    oll
    0.92
     regarder
    0.91
    оло
    0.90
    POSITIVE LOGITS
    šanu
    1.02
    yip
    0.97
    t
    0.97
    expectation
    0.97
    winkel
    0.96
    сіб
    0.95
    ఒ
    0.94
    보기
    0.92
    बा
    0.91
    别
    0.90
    Act Density 0.000%

    No Known Activations