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

    Neuronpedia

    INDEX
    Explanations

    references to specific variables or parameters in a technical or scientific context

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

    math symbols and LaTeX constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     racines
    -0.35
     retira
    -0.33
     FOOT
    -0.31
    Robot
    -0.31
     doigts
    -0.30
     Foot
    -0.30
     Maschine
    -0.29
    Style
    -0.29
     Chip
    -0.29
    lafen
    -0.29
    POSITIVE LOGITS
    ,\,\
    1.35
    Diweddarwch
    0.79
    SharedDtor
    0.74
    Personensuche
    0.73
    +:+
    0.69
    +#+
    0.68
     otomatig
    0.67
    requireNonNull
    0.67
     Numerade
    0.66
    TagMode
    0.65
    Act Density 0.032%

    No Known Activations