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

    Neuronpedia

    INDEX
    Explanations

    acid

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

    The neuron activates strongly for the term "acid" and related chemical/scientific terminology in scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     sorta
    -0.96
     сих
    -0.92
    migrationBuilder
    -0.88
    樹脂
    -0.88
    来年
    -0.81
    你说
    -0.79
     advocates
    -0.78
     соло
    -0.77
     administ
    -0.77
     honestly
    -0.77
    POSITIVE LOGITS
    acid
    1.13
    ulated
    1.05
    Acid
    1.04
     rain
    1.02
     reflux
    1.01
    ulous
    1.00
     acid
    0.98
    ophilus
    0.97
     احترام
    0.95
     corrosive
    0.94
    Act Density 0.037%

    No Known Activations