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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks commonly used for quotations

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

    quoted words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    -0.37
     I
    -0.34
     during
    -0.34
     Mad
    -0.33
    The
    -0.33
     infatti
    -0.31
     
    -0.31
     dagli
    -0.30
     since
    -0.29
     Zudem
    -0.29
    POSITIVE LOGITS
    expandindo
    0.93
    0.90
     Administrativna
    0.90
    <unused3>
    0.88
    <unused28>
    0.88
    [@BOS@]
    0.88
    <unused8>
    0.88
    <unused41>
    0.88
    <unused14>
    0.88
    <unused16>
    0.88
    Act Density 0.057%

    No Known Activations