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

    Neuronpedia

    INDEX
    Explanations

    finding input from output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     LeBron
    0.43
    公斤
    0.41
     Shopify
    0.40
    zak
    0.40
     Nickelodeon
    0.39
    ിക്കും
    0.39
    utiérrez
    0.38
    ptuous
    0.38
     গুজ
    0.38
     বড়
    0.37
    POSITIVE LOGITS
     enigma
    0.53
     enig
    0.52
     multivalued
    0.51
     dynamical
    0.49
     esoteric
    0.49
     nonlinear
    0.49
     unknown
    0.48
     elucid
    0.47
     insol
    0.46
     extrem
    0.45
    Act Density 0.001%

    No Known Activations