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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "first" and related temporal markers indicating the beginning of events or processes

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

    first occurrence of event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voud
    -0.35
    它的
    -0.33
    ieważ
    -0.32
     côtes
    -0.32
    élimin
    -0.30
     récla
    -0.30
    üns
    -0.30
     alqu
    -0.29
     its
    -0.29
    assertThat
    -0.29
    POSITIVE LOGITS
    windowFixed
    0.81
     فريبيس
    0.75
     blevet
    0.71
     betweenstory
    0.69
     kasarigan
    0.66
    toHaveBeenCalled
    0.65
     Wikimedijinoj
    0.63
    migrationBuilder
    0.60
    URLException
    0.59
     snippetHide
    0.59
    Act Density 0.026%

    No Known Activations