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

    Neuronpedia

    INDEX
    Explanations

    arthritis

    np_acts-logits-general · gemini-2.5-flash-lite

    commas followed by words in structured text, particularly in code, documentation, or formatted content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     or
    -1.06
    Only
    -1.02
     Only
    -1.00
     Despite
    -0.97
     Surprisingly
    -0.96
     Though
    -0.94
     Although
    -0.93
    herin
    -0.90
     While
    -0.89
     chose
    -0.89
    POSITIVE LOGITS
     inconveniente
    0.94
     consequences
    0.93
     boundaries
    0.91
     marki
    0.90
     ayudan
    0.88
    さぎ
    0.88
     マウス
    0.87
     deberes
    0.86
     stairs
    0.85
    closePath
    0.85
    Act Density 0.013%

    No Known Activations