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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quay
    -0.06
     mente
    -0.06
    _bel
    -0.06
     ranges
    -0.06
     Raq
    -0.06
    (scope
    -0.06
    річ
    -0.06
    ‌س
    -0.06
    佐
    -0.06
     خشک
    -0.05
    POSITIVE LOGITS
    irk
    0.07
     úřad
    0.06
    owania
    0.06
    ...",↵
    0.06
    :::::::::::::::
    0.06
     điều
    0.06
    ertility
    0.06
     ArgumentNullException
    0.06
     Teens
    0.06
    BIN
    0.06
    Act Density 0.007%

    No Known Activations