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

    Neuronpedia

    INDEX
    Explanations

    for loop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     рэгістрацыі
    0.51
    ็ก
    0.47
    inée
    0.45
    ดวก
    0.45
    idän
    0.45
    Roasted
    0.44
    惆
    0.44
    MaxIntensity
    0.44
     പോലെ
    0.44
     требованиям
    0.44
    POSITIVE LOGITS
     i
    0.59
     (
    0.52
    (
    0.48
    x
    0.47
    _
    0.46
     J
    0.44
    する
    0.44
    w
    0.44
     l
    0.44
     D
    0.44
    Act Density 0.055%

    No Known Activations