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
     ด
    -0.08
     Already
    -0.07
     Crack
    -0.06
     crackers
    -0.06
     Colony
    -0.06
    Ed
    -0.06
    ;:
    -0.06
     Features
    -0.06
    70
    -0.06
    	level
    -0.06
    POSITIVE LOGITS
    ereco
    0.07
    اسیون
    0.07
    給
    0.07
    GUI
    0.07
    Slice
    0.07
    gres
    0.07
    (dat
    0.06
    ุษย
    0.06
    рис
    0.06
    lied
    0.06
    Act Density 0.005%

    No Known Activations