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

    Neuronpedia

    INDEX
    Explanations

    dash or hyphenated numeric values

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

    ranges of numbers and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varandra
    -0.42
     palsu
    -0.37
     Infór
    -0.37
     peuples
    -0.37
     falsche
    -0.37
     étoient
    -0.36
     transparencia
    -0.35
     apareceu
    -0.35
     unicórnio
    -0.35
     irmã
    -0.35
    POSITIVE LOGITS
    rungsseite
    0.68
     يتيمه
    0.65
    uxxxx
    0.60
     propOrder
    0.57
    帖最后由
    0.55
     +/-
    0.54
     –
    0.53
    parsedMessage
    0.52
     }{@
    0.51
     jScrollPane
    0.51
    Act Density 0.111%

    No Known Activations