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

    Neuronpedia

    INDEX
    Explanations

    HTML class attributes related to elements of a webpage

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

    class attribute assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quite
    -0.43
     Quite
    -0.40
     ringan
    -0.40
    ⓘ
    -0.39
    Quite
    -0.38
     far
    -0.38
     weak
    -0.37
     }}"></
    -0.36
     otherwise
    -0.34
    ifndef
    -0.34
    POSITIVE LOGITS
     houſe
    0.68
     myſelf
    0.62
    TagMode
    0.59
    ⤹
    0.57
     pleaſure
    0.56
     poffe
    0.55
     chofe
    0.54
     ſta
    0.53
     Infórmanos
    0.52
     ſte
    0.51
    Act Density 0.017%

    No Known Activations