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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration and emotional connections

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

    expressed sentiment after determiner/auxiliary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.63
    parsedMessage
    -0.56
     informée
    -0.51
     surla
    -0.49
    UnitTesting
    -0.48
    msgTypes
    -0.48
     ProtoMessage
    -0.45
    itinéraire
    -0.44
     protoimpl
    -0.44
     jsPsych
    -0.43
    POSITIVE LOGITS
     dormitórios
    0.37
     fumée
    0.36
    brale
    0.36
     spéciaux
    0.36
     gyven
    0.35
     Wikimedijinoj
    0.35
    sproz
    0.35
    providedIn
    0.35
     religieuses
    0.35
     przeds
    0.35
    Act Density 0.094%

    No Known Activations