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

    Neuronpedia

    INDEX
    Explanations

    nested scopes or structures in programming language syntax

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

    references to namespaces or class definitions in programming code

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

    material fact, crime thriller

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.74
     pres
    -0.67
     and
    -0.65
     or
    -0.64
     -
    -0.63
     of
    -0.61
     trans
    -0.60
     pa
    -0.60
     bu
    -0.60
     jo
    -0.60
    POSITIVE LOGITS
    enumii
    1.22
     pleaſure
    1.21
     myſelf
    1.17
     bershka
    1.17
     theſe
    1.17
     itſelf
    1.15
     greateſt
    1.15
     Majefty
    1.13
     Theſe
    1.12
     ſch
    1.11
    Act Density 0.024%

    No Known Activations