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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "super"

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

    super followed by dealloc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rö
    -0.31
     beginnetje
    -0.31
    IRQ
    -0.31
     '\\;'
    -0.31
     teeth
    -0.31
    Obrázky
    -0.30
     layui
    -0.30
     tef
    -0.29
    ETIME
    -0.29
    haya
    -0.28
    POSITIVE LOGITS
     super
    1.52
    super
    1.28
     SUPER
    1.14
     Super
    1.13
    Super
    1.09
     супер
    1.08
    SUPER
    1.01
     súper
    0.98
    Супер
    0.90
     siêu
    0.89
    Act Density 0.002%

    No Known Activations