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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and specific references

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

    sports player names and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -1.14
    setVerticalGroup
    -1.03
    AndEndTag
    -1.02
     Paglinawan
    -0.94
     cherchés
    -0.93
    ValueStyle
    -0.92
    __":
    -0.87
     ―――――
    -0.83
    InitVars
    -0.82
    AxisAlignment
    -0.79
    POSITIVE LOGITS
     play
    0.56
     plays
    0.54
     played
    0.54
    PLAY
    0.50
     playing
    0.48
     scored
    0.45
     inscrit
    0.44
    '
    0.44
     mencetak
    0.44
    спи
    0.43
    Act Density 0.035%

    No Known Activations