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

    Neuronpedia

    INDEX
    Explanations

    programming commands and functions related to running tests or processes

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

    finally doing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.46
     الرياضيه
    -0.42
     Particularly
    -0.42
    Especially
    -0.41
     newer
    -0.39
     linkovi
    -0.39
     क्यों
    -0.39
     CERTAIN
    -0.39
     gouver
    -0.39
     particularmente
    -0.38
    POSITIVE LOGITS
     actual
    1.38
    actual
    1.21
    Actual
    1.09
     Actual
    1.09
     eigentliche
    1.07
    実際に
    1.03
     ACTUAL
    1.02
     actually
    1.02
    いよいよ
    1.02
     proprement
    1.01
    Act Density 0.126%

    No Known Activations