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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicated by the word "if."

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

    following "if"

    np_acts-logits-general · gemini-2.0-flash

    if clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.48
    elo
    -0.40
    HTML
    -0.38
    zz
    -0.38
     acus
    -0.38
    ano
    -0.38
    angular
    -0.37
    FlatList
    -0.36
     audience
    -0.35
     foule
    -0.35
    POSITIVE LOGITS
     if
    0.90
     gdyby
    0.81
     אם
    0.73
     dacă
    0.73
     wenn
    0.73
     jika
    0.71
     invokingState
    0.71
    jména
    0.68
    if
    0.67
    rungsseite
    0.67
    Act Density 0.188%

    No Known Activations