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

    Neuronpedia

    INDEX
    Explanations

    references to actions and decisions related to change and progress

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

    following forms of "go"

    np_acts-logits-general · gemini-2.0-flash

    gone further

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.72
     ويكيميديا
    -0.67
     noqa
    -0.65
     مشين
    -0.63
     AssemblyCompany
    -0.61
     htons
    -0.60
     Wikimedijinoj
    -0.57
     bArr
    -0.52
    TagHelper
    -0.51
    apy
    -0.51
    POSITIVE LOGITS
     further
    1.29
    further
    1.15
     addirittura
    1.08
    さらに
    1.06
     sogar
    0.99
     zelfs
    0.98
     additionally
    0.98
    更に
    0.96
     FURTHER
    0.95
     even
    0.94
    Act Density 0.392%

    No Known Activations