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

    Neuronpedia

    INDEX
    Explanations

    evidence and findings related to research conclusions and definitions

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

    Followed by "that."

    np_acts-logits-general · gemini-2.0-flash

    reporting research findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.83
     beginnetje
    -0.76
     समीक्षाओं
    -0.71
     tartalomajánló
    -0.71
     IUPAC
    -0.68
     समीक्षाएं
    -0.66
     ويكيميديا
    -0.64
    SequentialGroup
    -0.62
    stdc
    -0.62
    PhysRev
    -0.62
    POSITIVE LOGITS
     significant
    0.88
     evidence
    0.78
     clearly
    0.74
     substantial
    0.72
     conclusively
    0.67
     considerable
    0.67
     how
    0.66
     clear
    0.65
    considerable
    0.65
    clearly
    0.64
    Act Density 0.710%

    No Known Activations