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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and concepts related to data performance and statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pure depression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.66
     Administrativna
    -0.64
    transQ
    -0.62
    NameInMap
    -0.61
     surla
    -0.58
     pérd
    -0.56
     Paglinawan
    -0.56
     հղումներ
    -0.55
    TagMode
    -0.51
     increí
    -0.50
    POSITIVE LOGITS
     and
    0.48
     F
    0.42
     
    0.42
     des
    0.41
     a
    0.40
     the
    0.39
    0.39
     "
    0.38
     Mat
    0.38
     Wolff
    0.38
    Act Density 0.498%
    No Known Activations