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

    Neuronpedia

    INDEX
    Explanations

    nested function calls with specific parameters and condition checks

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

    random integer generation and 'HELLO'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.55
    pecabe
    -0.54
     faſt
    -0.54
    Hentet
    -0.54
     Reſ
    -0.50
    gucig
    -0.49
     myſelf
    -0.49
     enfans
    -0.48
     Majefty
    -0.47
    Personendaten
    -0.47
    POSITIVE LOGITS
    listdir
    0.54
    randint
    0.49
     Random
    0.46
    السكان
    0.45
    rand
    0.45
     Савезне
    0.44
     randomly
    0.44
    Random
    0.43
     random
    0.41
    preter
    0.41
    Act Density 0.016%

    No Known Activations