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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" associated with numerical values

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

    Code snippets or unusual symbols

    np_acts-logits-general · gemini-2.0-flash

    contact or reach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lap
    -0.56
     Lap
    -0.55
     Ent
    -0.54
     ModelRenderer
    -0.53
     visibles
    -0.52
    信
    -0.52
    acji
    -0.52
    Ent
    -0.51
     interference
    -0.51
    ATE
    -0.50
    POSITIVE LOGITS
     nakalista
    0.77
    MENAFN
    0.74
    انجليز
    0.72
    ParallelGroup
    0.71
    ptonshire
    0.71
    InjectAttribute
    0.71
     Wikispecies
    0.71
     tartalomajánló
    0.69
     мәкал
    0.69
     الرياضيه
    0.69
    Act Density 0.291%

    No Known Activations