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

    Neuronpedia

    INDEX
    Explanations

    words related to communication and expression of information

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

    less is known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Statistiche
    -0.36
     olev
    -0.30
     vitória
    -0.30
     voulez
    -0.30
     glauben
    -0.29
     padrões
    -0.29
     empate
    -0.28
    cení
    -0.28
     elä
    -0.28
    change
    -0.27
    POSITIVE LOGITS
    osoba
    0.66
     الحره
    0.66
     الرياضيه
    0.65
    StoryboardSegue
    0.63
    ロウィン
    0.61
    zzleHttp
    0.61
     propOrder
    0.61
     kasarigan
    0.59
     الاطلاع
    0.59
    0.59
    Act Density 0.052%

    No Known Activations