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

    Neuronpedia

    INDEX
    Explanations

    intrinsic exertion, abstract theory, successful exploitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    1.11
    E
    1.09
    ES
    1.02
    ponible
    1.01
    ESA
    1.00
    А
    1.00
    ESO
    0.99
    AC
    0.95
    Y
    0.93
    S
    0.93
    POSITIVE LOGITS
    weds
    1.75
    stood
    1.45
    icularly
    1.39
    swering
    1.29
    lapping
    1.26
    ங்கிணை
    1.25
     пришлось
    1.23
    orems
    1.22
     lLoginID
    1.21
    这也是
    1.20
    Act Density 0.856%

    No Known Activations