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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal involvement or requests in dialogues

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

    First-person expression of gratitude or hope

    np_acts-logits-general · gemini-2.0-flash

    speaker's intention or sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nodoc
    -0.65
    bcryptjs
    -0.63
     betweenstory
    -0.62
    üyada
    -0.62
    Referencie
    -0.59
    
    -0.59
    createCanvas
    -0.56
    resave
    -0.56
    IntoConstraints
    -0.56
    PreferredItem
    -0.55
    POSITIVE LOGITS
     hope
    1.01
    hope
    0.77
     wish
    0.69
    Hope
    0.69
     hopes
    0.69
     promise
    0.65
     Hope
    0.64
     sincerely
    0.64
     nadzieję
    0.63
     wünschen
    0.63
    Act Density 0.178%

    No Known Activations