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

    Neuronpedia

    INDEX
    Explanations

    Gross dividend calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StubCompat
    0.43
    evším
    0.42
    ต่างๆ
    0.40
    PROC
    0.39
    AllRef
    0.39
    Fotos
    0.39
    CHEMICAL
    0.39
    nonlinear
    0.38
    叅
    0.38
     സഹ
    0.38
    POSITIVE LOGITS
     Verdict
    0.45
    inal
    0.42
    uci
    0.40
    yes
    0.40
    rove
    0.39
    r
    0.39
    巒
    0.39
    ্বার
    0.39
    ens
    0.38
    as
    0.38
    Act Density 0.001%

    No Known Activations