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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and questions involving the word "if."

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

    asking if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.43
    TargetException
    -0.41
    hæng
    -0.40
    Traceback
    -0.39
    tonsoft
    -0.39
     trasferimento
    -0.39
     useHistory
    -0.39
     trouverez
    -0.39
    WebServlet
    -0.39
    TemporalType
    -0.38
    POSITIVE LOGITS
     האם
    0.68
     apakah
    0.66
     whether
    0.63
    Czy
    0.62
     jestli
    0.58
     nonUne
    0.57
     Apakah
    0.56
     Czy
    0.56
    whether
    0.55
    checkIf
    0.55
    Act Density 0.012%

    No Known Activations