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

    Neuronpedia

    INDEX
    Explanations

    references to complete lists and comprehensive details

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

    completing lists, data, definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kaynakça
    -0.40
    рио
    -0.36
    KHz
    -0.34
    varargin
    -0.34
     gag
    -0.31
     strto
    -0.31
    Ү
    -0.31
    Viel
    -0.30
     Ansch
    -0.30
     little
    -0.30
    POSITIVE LOGITS
    complete
    1.41
     Complete
    1.38
     complete
    1.38
    Complete
    1.34
     COMPLETE
    1.25
    COMPLETE
    1.20
     completos
    1.19
     completo
    1.18
     completa
    1.13
     completas
    1.09
    Act Density 0.022%

    No Known Activations