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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special symbols

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

    Text followed by colons or brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers and specific terms like "final"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     N
    -0.58
     S
    -0.58
     No
    -0.58
     a
    -0.56
     L
    -0.56
     “
    -0.56
     I
    -0.56
     E
    -0.55
     P
    -0.55
     Al
    -0.55
    POSITIVE LOGITS
     
    1.13
     Theſe
    1.01
     Monfieur
    0.92
     myſelf
    0.88
     themſelves
    0.87
     Shakspeare
    0.87
     quæ
    0.86
     itſelf
    0.85
     uſed
    0.82
     becauſe
    0.80
    Act Density 2.142%

    No Known Activations