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

    Neuronpedia

    INDEX
    Explanations

    sentences with emotional expressions or moments of vulnerability

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

    Punctuation and newline placement

    np_acts-logits-general · gemini-2.0-flash

    Nobleman, Queen, he

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.88
    ロウィン
    -0.83
     ब्रेकडाउन
    -0.79
    нгред
    -0.79
    出版年
    -0.72
     queſta
    -0.69
    ſicht
    -0.69
    <unused41>
    -0.69
    <unused3>
    -0.68
    <unused14>
    -0.68
    POSITIVE LOGITS
     Sinne
    0.30
    Taking
    0.29
    想到
    0.29
     tå
    0.28
    Me
    0.26
    His
    0.26
     obs
    0.26
    Let
    0.25
    Oh
    0.25
     Oh
    0.25
    Act Density 0.134%

    No Known Activations