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

    Neuronpedia

    INDEX
    Explanations

    references to the letter 'G'

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

    Followed by specific non-English tokens/words

    np_acts-logits-general · gemini-2.0-flash

    G followed by specific sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.57
     /\.
    -0.49
    postmedia
    -0.48
    esModule
    -0.47
     within
    -0.46
     perfect
    -0.45
     immediate
    -0.45
     Immediate
    -0.44
    wieś
    -0.44
    PerformLayout
    -0.43
    POSITIVE LOGITS
     Matériau
    0.67
     perfons
    0.66
     informée
    0.63
    InitVars
    0.62
    存于互联网档案馆
    0.59
     Paulus
    0.57
     shewn
    0.57
     calendriers
    0.57
     كومونز
    0.56
     perſon
    0.55
    Act Density 0.198%

    No Known Activations