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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    地方
    -0.06
     isAuthenticated
    -0.06
    49
    -0.06
    Topics
    -0.06
    ieur
    -0.06
     */↵↵↵
    -0.06
     debugging
    -0.06
    253
    -0.05
     persuaded
    -0.05
     spice
    -0.05
    POSITIVE LOGITS
    _books
    0.07
    speaker
    0.07
    BOOL
    0.06
     JFrame
    0.06
     всі
    0.06
     当
    0.06
     conse
    0.06
    朗
    0.06
     alas
    0.06
    uele
    0.06
    Act Density 0.301%

    No Known Activations