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

    Neuronpedia

    INDEX
    Explanations

    expressions related to communication and the sharing of thoughts or experiences

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

    speaking about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cellaneous
    -0.55
    лтамалар
    -0.48
    راتيج
    -0.47
     Réponses
    -0.44
    endpush
    -0.43
     विश्वसनीयता
    -0.43
    pitaux
    -0.42
    styleType
    -0.42
    httphttps
    -0.42
    prüche
    -0.40
    POSITIVE LOGITS
     about
    0.79
     tentang
    0.71
     apie
    0.71
    about
    0.69
     talked
    0.67
     parlent
    0.66
     hablar
    0.66
     talk
    0.66
     talking
    0.66
     parler
    0.65
    Act Density 0.125%

    No Known Activations