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

    Neuronpedia

    INDEX
    Explanations

    speed, double, sip, squeeze, high, Horseshoe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     были
    0.58
     партне
    0.55
     خوات
    0.54
    örer
    0.51
     shabby
    0.50
     membr
    0.49
     сум
    0.49
    कुमारी
    0.48
     брен
    0.48
     الكتب
    0.48
    POSITIVE LOGITS
    et
    0.51
    Fel
    0.47
    I
    0.47
    ing
    0.46
    o
    0.46
    installation
    0.45
    리스
    0.44
    y
    0.44
    u
    0.43
     scanning
    0.43
    Act Density 0.000%

    No Known Activations