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

    Neuronpedia

    INDEX
    Explanations

    references to phases and elements associated with bonuses or initial conditions

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

    initial advantage or beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FileDescriptor
    -0.42
    furt
    -0.39
    urlpatterns
    -0.39
    Gotcha
    -0.38
    HORE
    -0.37
    balt
    -0.36
    synthesize
    -0.36
    vaných
    -0.36
     skippy
    -0.35
     consumer
    -0.35
    POSITIVE LOGITS
    initial
    0.69
     Initial
    0.68
     initial
    0.66
    Initial
    0.64
     INITIAL
    0.63
    初始
    0.63
    PreExecute
    0.60
     초기
    0.58
     iniziale
    0.56
    rungsseite
    0.54
    Act Density 0.315%

    No Known Activations