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

    Neuronpedia

    INDEX
    Explanations

    leap forward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ducers
    0.39
    pires
    0.39
    illiams
    0.39
    貴重
    0.39
    )|$(
    0.39
    gnet
    0.37
     dini
    0.37
    が通販できます
    0.37
     Regener
    0.37
    াদ্র
    0.36
    POSITIVE LOGITS
     leap
    1.87
     leaps
    1.73
     jump
    1.51
     breakthrough
    1.51
     leapt
    1.50
     Leap
    1.49
     leaped
    1.48
    跳
    1.46
     leaping
    1.41
     jumps
    1.39
    Act Density 0.014%

    No Known Activations