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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to fashion and styling

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

    following "or", "of", or "his"

    np_acts-logits-general · gemini-2.0-flash

    his transgression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.69
    #+#
    -0.65
     }}"></
    -0.59
     ?>>
    -0.58
     picioare
    -0.57
     }</
    -0.56
     équilibr
    -0.55
    はじめに
    -0.54
    Tazama
    -0.53
     Socks
    -0.52
    POSITIVE LOGITS
     flow
    0.75
     Flow
    0.58
    databind
    0.58
     scoop
    0.56
    flow
    0.55
     cute
    0.55
    AndEndTag
    0.54
    potranspiration
    0.53
     tank
    0.52
     sund
    0.52
    Act Density 0.106%

    No Known Activations