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

    Neuronpedia

    INDEX
    Explanations

    instances of HTML or XML elements and their attributes

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

    questions or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.85
     الرياضيه
    -0.77
    Autoritní
    -0.77
    AnchorStyles
    -0.76
     Italijani
    -0.71
    CloseOperation
    -0.69
    -0.69
    Personendaten
    -0.68
    -0.66
    StoryboardSegue
    -0.64
    POSITIVE LOGITS
    
    0.57
     []:
    0.35
    Acceptance
    0.27
    Periodic
    0.27
     paddles
    0.27
    Years
    0.26
    Front
    0.26
    Te
    0.26
    出
    0.26
    Heavy
    0.25
    Act Density 0.017%

    No Known Activations