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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and logical constructs in code

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

    Followed by "if" (or variants of "if")

    np_acts-logits-general · gemini-2.0-flash

    conditional logic ("if")

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dougall
    -0.53
     block
    -0.51
    laye
    -0.47
     ốc
    -0.46
    upra
    -0.46
    eny
    -0.46
    atyw
    -0.46
    Empereur
    -0.45
     рода
    -0.45
     blocked
    -0.44
    POSITIVE LOGITS
     if
    1.33
    if
    1.32
     nếu
    1.05
     dacă
    1.00
     если
    0.94
    If
    0.92
     jika
    0.91
     If
    0.89
     якщо
    0.86
     jeśli
    0.86
    Act Density 0.051%

    No Known Activations