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

    Neuronpedia

    INDEX
    Explanations

    first-person narratives and personal experiences

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

    "I" or a name followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    When I X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     never
    -0.70
    never
    -0.68
     nigdy
    -0.67
     никогда
    -0.66
     nikdy
    -0.63
     luôn
    -0.59
    Never
    -0.59
    always
    -0.59
     always
    -0.58
     Never
    -0.58
    POSITIVE LOGITS
     finally
    0.89
     المعيارى
    0.79
     inevitably
    0.78
    NUMX
    0.77
    finally
    0.75
    躇
    0.74
     enters
    0.73
     väl
    0.73
     reaches
    0.73
     Schließlich
    0.71
    Act Density 0.263%

    No Known Activations