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

    Neuronpedia

    INDEX
    Explanations

    strong indicators of a sequence or timeline in events

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

    First, after, when, on, as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.90
     tartalomajánló
    -0.88
     الرياضيه
    -0.83
    AndEndTag
    -0.78
     Италијани
    -0.77
    Хьажоргаш
    -0.75
    -0.75
    yntaxException
    -0.71
    MigrationBuilder
    -0.71
    WriteBarrier
    -0.70
    POSITIVE LOGITS
    Predecesor
    0.29
     Erfolgs
    0.29
     Merkmale
    0.28
     elde
    0.28
     murió
    0.28
     wśród
    0.27
     okaza
    0.26
     Erwartungen
    0.25
    Results
    0.25
     gelangen
    0.24
    Act Density 0.066%

    No Known Activations