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

    Neuronpedia

    INDEX
    Explanations

    for context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     :#
    0.47
    함으로써
    0.47
    द्वारे
    0.46
    อาจ
    0.46
     poprzez
    0.44
    θη
    0.44
    Да
    0.44
     によって
    0.43
    穿
    0.43
     Britney
    0.43
    POSITIVE LOGITS
    e
    0.45
    il
    0.43
    elen
    0.42
    ird
    0.41
    sset
    0.40
    successful
    0.40
    em
    0.40
    ட்ரோ
    0.39
    el
    0.39
    in
    0.38
    Act Density 0.000%

    No Known Activations