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

    Neuronpedia

    INDEX
    Explanations

    sentences containing specific phrases or terms that indicate communication or messaging

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

    share with you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tria
    -0.42
    endencies
    -0.39
    empêcher
    -0.35
     comisiones
    -0.34
    roned
    -0.34
     wnios
    -0.34
     szczegó
    -0.34
    acán
    -0.33
    Prevention
    -0.33
     idéale
    -0.32
    POSITIVE LOGITS
    AndEndTag
    0.67
    MessageOf
    0.65
     Италијани
    0.65
    Vidite
    0.63
    VYMaps
    0.62
     kaarangay
    0.59
     Мексичка
    0.57
    parsedMessage
    0.55
    хьтан
    0.53
    دانشنامهٔ
    0.52
    Act Density 0.017%

    No Known Activations