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

    Neuronpedia

    INDEX
    Explanations

    LaTeX math environments and related syntax

    oai_token-act-pair · gemini-2.0-flash

    commands or keywords related to left orientation or movement

    np_token-act-pair-logits · gpt-4o-mini

    left

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )</
    -1.00
    ?)
    -0.99
    ）
    -0.92
    ！）
    -0.90
     ）
    -0.88
    >)</
    -0.85
    ?).
    -0.85
    !)
    -0.85
    .”)
    -0.85
     )
    -0.83
    POSITIVE LOGITS
    left
    1.12
     left
    0.87
    RenderAtEndOf
    0.68
     laiss
    0.68
    左
    0.66
     Left
    0.66
     مشين
    0.65
     leaves
    0.64
    Left
    0.64
     leave
    0.64
    Act Density 0.375%

    No Known Activations