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

    Neuronpedia

    INDEX
    Explanations

    references to a specific context or situation

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

    user input signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -1.20
    AndEndTag
    -1.11
     nahilalakip
    -1.09
     Administrativna
    -1.03
     Signalez
    -1.03
     autorytatywna
    -1.02
    تقاوى
    -1.01
    verwijspagina
    -1.00
     continúas
    -0.99
    expandindo
    -0.98
    POSITIVE LOGITS
    
    0.77
    !
    0.41
     
    0.41
    l
    0.38
     ?
    0.37
    qu
    0.36
    la
    0.36
     !
    0.36
     +
    0.35
    w
    0.35
    Act Density 0.000%

    No Known Activations