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

    Neuronpedia

    INDEX
    Explanations

    status updates or results of operations, particularly those indicating success or failure

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

    success=true, false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    telek
    -0.46
    StructEnd
    -0.44
    Custo
    -0.38
    Kamp
    -0.38
    Fine
    -0.38
    vegli
    -0.38
    ornment
    -0.38
    MetaType
    -0.38
     gang
    -0.38
    wiek
    -0.37
    POSITIVE LOGITS
     насељу
    0.64
     nahilalakip
    0.55
    Hentet
    0.46
     kasarigan
    0.45
    kuuta
    0.44
    ésultat
    0.44
    ExtendWith
    0.44
     <<<<<<<<<<<<<<
    0.43
     AssemblyCulture
    0.43
    RegressionTest
    0.42
    Act Density 0.006%

    No Known Activations