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

    Neuronpedia

    INDEX
    Explanations

    percentage-related phrases and statistics

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

    percent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    -0.50
    arbeitung
    -0.34
    </strong>
    -0.34
     loup
    -0.32
     Técnica
    -0.30
    keyboardType
    -0.29
    の
    -0.29
    ://
    -0.29
     Defensa
    -0.29
    ing
    -0.29
    POSITIVE LOGITS
     propOrder
    0.88
    ſſung
    0.81
    <unused20>
    0.80
    <unused42>
    0.80
    <unused79>
    0.80
    <unused16>
    0.80
    <unused52>
    0.80
    <unused74>
    0.80
    [@BOS@]
    0.79
    <unused8>
    0.79
    Act Density 0.004%

    No Known Activations