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

    Neuronpedia

    INDEX
    Explanations

    strings that look like academic citations

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jagung
    -0.38
     twin
    -0.35
     toward
    -0.35
     fotó
    -0.34
    re
    -0.33
    المناصب
    -0.32
     signals
    -0.31
    ignite
    -0.30
    null
    -0.30
    Passive
    -0.30
    POSITIVE LOGITS
     незавершена
    0.84
    KommentareTeilen
    0.76
    ftagPool
    0.73
    رشف
    0.72
    SourceChecksum
    0.70
     समीक्षक
    0.70
     lenker
    0.70
     Signalez
    0.69
    sidemargin
    0.68
     الحره
    0.66
    Act Density 0.529%

    No Known Activations