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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate reported speech or quotations

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

    Follows a quotation mark or comma

    np_acts-logits-general · gemini-2.0-flash

    reports conclusions and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dafx
    -0.50
    召喚
    -0.46
    Становништво
    -0.44
     Infórmanos
    -0.44
    IsContent
    -0.43
    وفة
    -0.42
    indsay
    -0.41
    marginHorizontal
    -0.41
     tweezers
    -0.41
    inkai
    -0.40
    POSITIVE LOGITS
     aldus
    0.53
     concluded
    0.50
     concluyó
    0.49
     avsl
    0.48
     resourceCulture
    0.46
     ajouté
    0.46
     concludes
    0.44
     agregó
    0.44
     añadió
    0.43
     stressed
    0.42
    Act Density 0.044%

    No Known Activations