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

    Neuronpedia

    INDEX
    Explanations

    references to professional roles and career advancements

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

    apprentice and assistant roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.49
     nakalista
    -0.47
    rungsseite
    -0.47
    LEncoder
    -0.47
     المتحدة
    -0.46
    twimg
    -0.45
    iname
    -0.43
     skak
    -0.43
    scriptcase
    -0.43
    estrian
    -0.43
    POSITIVE LOGITS
     للاسماء
    0.43
     trabajó
    0.38
    ᅠ
    0.33
    verifyException
    0.32
    hoeddwyd
    0.32
    enterOuterAlt
    0.31
    spent
    0.31
     spent
    0.31
     géant
    0.30
     trabajando
    0.30
    Act Density 0.018%

    No Known Activations