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

    Neuronpedia

    INDEX
    Explanations

    equality signs and their associated structures in code

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

    syscall and CREATE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.67
     ModelExpression
    -0.66
     Administrativna
    -0.65
     <=",
    -0.63
    󠁢
    -0.60
     Chwiliwch
    -0.59
    новништво
    -0.58
     оригіналу
    -0.58
    Portail
    -0.54
    expandindo
    -0.54
    POSITIVE LOGITS
    CodeAttribute
    0.34
    참고
    0.32
    AutoScale
    0.31
    อัน
    0.26
    ското
    0.26
     دائ
    0.26
    </sub>
    0.26
     perpé
    0.26
    Generated
    0.25
    LoadMore
    0.25
    Act Density 0.004%

    No Known Activations