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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entityId
    -0.08
    	TR
    -0.07
     eleven
    -0.07
    걸
    -0.06
    鐵
    -0.06
    ，当
    -0.06
     anarchist
    -0.06
    ≦
    -0.06
    (theta
    -0.06
     شهرستان
    -0.06
    POSITIVE LOGITS
     bosses
    0.06
    lage
    0.06
    ucceeded
    0.06
    lobs
    0.06
    arsimp
    0.06
    The
    0.06
    :expr
    0.06
    Press
    0.06
    (Locale
    0.06
    chedulers
    0.06
    Act Density 0.127%

    No Known Activations