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

    Neuronpedia

    INDEX
    Explanations

    the letter 'h' in various contexts throughout the text

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

    h followed by mathematical or code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.66
    Tikang
    -0.65
    Diweddarwch
    -0.60
     betweenstory
    -0.59
    +#+#
    -0.57
    amie
    -0.57
    expandindo
    -0.57
    parsedMessage
    -0.57
    Portale
    -0.56
    ->___
    -0.54
    POSITIVE LOGITS
     h
    1.70
     H
    0.81
    ｈ
    0.70
     х
    0.62
    setH
    0.56
     b
    0.56
     r
    0.53
     alugar
    0.52
     ht
    0.51
     ه
    0.50
    Act Density 0.016%

    No Known Activations