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

    Neuronpedia

    INDEX
    Explanations

    metadata

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qi
    -0.07
    _Word
    -0.07
    롬
    -0.06
    parts
    -0.06
     needless
    -0.06
    """),↵
    -0.06
     pharm
    -0.06
    篁
    -0.06
    .WriteAllText
    -0.06
     rdr
    -0.06
    POSITIVE LOGITS
    تركيز
    0.07
     Proposed
    0.07
    olan
    0.07
     ושל
    0.07
    чрежден
    0.06
    딫
    0.06
    Fish
    0.06
    .bluetooth
    0.06
    \/
    0.06
    irms
    0.06
    Act Density 0.011%

    No Known Activations