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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pine
    -0.08
     speedy
    -0.07
    ӱ
    -0.07
    ᐃ
    -0.07
     العلي
    -0.07
    🏽
    -0.07
    갛
    -0.07
    ሐ
    -0.07
     UC
    -0.06
     whale
    -0.06
    POSITIVE LOGITS
    SU
    0.07
    FW
    0.07
    文化底蕴
    0.07
    erton
    0.07
     graduated
    0.07
     brokers
    0.06
    FIELD
    0.06
    DAY
    0.06
    坊
    0.06
    ZW
    0.06
    Act Density 0.015%

    No Known Activations