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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating personal or collective identity

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

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dirait
    -0.39
     siquiera
    -0.38
    icionar
    -0.37
    íté
    -0.37
     dessutom
    -0.36
     MainAxisSize
    -0.35
     prêtres
    -0.35
     seluruh
    -0.35
     davantage
    -0.34
     Priester
    -0.33
    POSITIVE LOGITS
    principalColumn
    0.65
    LookAnd
    0.61
     للاسماء
    0.56
    ThroughAttribute
    0.54
     Wikimedijinoj
    0.54
    sizeCache
    0.53
    UIControlState
    0.51
     Administrativna
    0.51
     mitä
    0.51
    aarrggbb
    0.51
    Act Density 0.072%

    No Known Activations