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

    Neuronpedia

    INDEX
    Explanations

    legal and regulatory terms related to liability and compliance

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

    Technical or scientific writing

    np_acts-logits-general · gemini-2.0-flash

    mechanism, smaller scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    phorus
    -0.57
     T
    -0.57
    uffff
    -0.52
     di
    -0.50
    ↵
    -0.50
     W
    -0.50
    <eos>
    -0.49
    oneg
    -0.49
    jspx
    -0.49
     ra
    -0.49
    POSITIVE LOGITS
     Theſe
    1.05
     houſe
    1.00
     myſelf
    1.00
     Monfieur
    0.96
    ſelf
    0.92
     Efq
    0.92
     pleaſure
    0.92
     whoſe
    0.90
     ſeveral
    0.89
    .",
    0.89
    Act Density 1.352%

    No Known Activations