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

    Neuronpedia

    INDEX
    Explanations

    return statements and their associated values in programming code

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

    return false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.63
     autorytatywna
    -0.53
     Meksiku
    -0.53
     समीक्षाओं
    -0.52
     nhàng
    -0.50
    NewUrlParser
    -0.49
    TagMode
    -0.48
    المكان
    -0.47
    Izvori
    -0.47
    يكب
    -0.47
    POSITIVE LOGITS
     false
    0.63
    false
    0.58
     False
    0.46
    False
    0.45
     falsas
    0.45
     falsehood
    0.41
    hören
    0.40
    FALSE
    0.39
     less
    0.38
    ashi
    0.36
    Act Density 0.005%

    No Known Activations