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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation used in equations, particularly related to matrix operations

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

    LaTeX or mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كومونز
    -0.64
    Xna
    -0.62
    windowFixed
    -0.59
    gdx
    -0.55
    </strong>
    -0.54
    DockStyle
    -0.54
     PyQt
    -0.53
    |[]
    -0.52
    bootstrapcdn
    -0.52
    :[],
    -0.52
    POSITIVE LOGITS
    ↵↵
    0.83
    ↵↵↵↵
    0.69
    </blockquote>
    0.65
    ↵↵↵
    0.64
    ↵↵↵↵↵↵↵↵
    0.63
    ↵↵↵↵↵
    0.63
    ]--;
    0.62
    <eos>
    0.61
    ↵↵↵↵↵↵
    0.61
    ]]]
    0.60
    Act Density 0.170%

    No Known Activations