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
    /mm
    -0.07
     conquer
    -0.06
    ũng
    -0.06
     appointments
    -0.06
    該
    -0.06
    mega
    -0.06
    .links
    -0.06
    Billy
    -0.06
    òi
    -0.06
    -side
    -0.06
    POSITIVE LOGITS
    lut
    0.06
     [];
    0.06
     "\↵
    0.06
    (defun
    0.06
     pruning
    0.06
     yatırım
    0.06
     observing
    0.06
    	dx
    0.06
    ATRIX
    0.06
     внутри
    0.06
    Act Density 0.005%

    No Known Activations