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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    を利用して
    -0.08
    澳大
    -0.08
    简直就是
    -0.08
     resumes
    -0.07
     واست
    -0.07
    -parse
    -0.07
    إست
    -0.07
    ствовать
    -0.07
    Spain
    -0.07
     değerlendir
    -0.07
    POSITIVE LOGITS
    AGIC
    0.07
    🔹
    0.07
     Marshall
    0.07
    	thread
    0.07
     Mechanics
    0.07
     Gefühl
    0.06
     bullet
    0.06
    _initial
    0.06
    ём
    0.06
     #(
    0.06
    Act Density 0.051%

    No Known Activations