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

    Neuronpedia

    INDEX
    Explanations

    coding-related structures and functions

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

    Code snippets with variables (txt, obj, pref)

    np_acts-logits-general · gemini-2.0-flash

    old english text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     di
    -0.49
     van
    -0.49
     
    -0.49
     S
    -0.47
     au
    -0.47
     Di
    -0.46
    ↵↵
    -0.45
     da
    -0.44
     cons
    -0.44
     te
    -0.44
    POSITIVE LOGITS
     itſelf
    1.13
     referenties
    1.12
     iſt
    1.12
     myſelf
    1.11
     Majefty
    1.01
     Eſ
    1.01
     ſeveral
    1.00
     ddelweddau
    1.00
     Monfieur
    0.99
     greateſt
    0.99
    Act Density 0.553%

    No Known Activations