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

    Neuronpedia

    INDEX
    Explanations

    machine learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prince
    -0.06
     Ruf
    -0.06
     genera
    -0.06
     Exist
    -0.06
    nama
    -0.06
     countryCode
    -0.06
     알
    -0.06
     SCREEN
    -0.06
    vero
    -0.06
     Hotel
    -0.06
    POSITIVE LOGITS
    ezpeč
    0.07
    طبي
    0.06
    <style
    0.06
    _SECURITY
    0.06
    (paths
    0.06
    chool
    0.06
    _friends
    0.06
    ційна
    0.06
    ständ
    0.06
                    ↵
    0.06
    Act Density 0.037%

    No Known Activations