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

    Neuronpedia

    INDEX
    Explanations

    specific Java import statements

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

    while or among

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '{@
    -0.75
    featureID
    -0.66
    SharedDtor
    -0.65
    PYX
    -0.62
    setVerticalGroup
    -0.59
     kaarangay
    -0.59
    AnimationsModule
    -0.58
    DockStyle
    -0.58
    :✨
    -0.57
    verifyException
    -0.55
    POSITIVE LOGITS
    tôi
    0.43
    neté
    0.40
     poros
    0.38
     importe
    0.38
    [toxicity=0]
    0.36
     teile
    0.36
    是我们
    0.35
    Computing
    0.34
     디자인
    0.34
     kartą
    0.34
    Act Density 0.001%

    No Known Activations