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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tü
    -0.07
    xcb
    -0.07
    옯
    -0.07
    nm
    -0.07
    一一
    -0.07
    	index
    -0.07
    itra
    -0.07
    עיד
    -0.06
     gj
    -0.06
    ��이
    -0.06
    POSITIVE LOGITS
    맊
    0.08
     abilities
    0.07
    Originally
    0.07
     Simpsons
    0.07
     Mandarin
    0.07
     Tomato
    0.07
     schemas
    0.07
     unfolded
    0.07
    톢
    0.07
     POL
    0.07
    Act Density 0.008%

    No Known Activations