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

    Neuronpedia

    INDEX
    Explanations

    closing brackets or curly braces in code

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

    Code snippets/fragments

    np_acts-logits-general · gemini-2.0-flash

    transition set test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     past
    -1.57
    past
    -1.38
     Past
    -1.31
    Past
    -1.31
     Vergangenheit
    -1.18
     PAST
    -1.16
     passato
    -1.07
     pasado
    -1.06
    PAST
    -1.04
     passado
    -0.91
    POSITIVE LOGITS
    Úl
    0.50
    ↵↵
    0.49
    AddRange
    0.48
    makeText
    0.47
    roppo
    0.47
     jadx
    0.45
     hại
    0.44
    velop
    0.43
    %$
    0.43
    lüğü
    0.43
    Act Density 0.072%

    No Known Activations