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

    Neuronpedia

    INDEX
    Explanations

    .model .entity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reset
    -0.07
     StatusBar
    -0.07
    иф
    -0.07
     vot
    -0.06
     put
    -0.06
    'D
    -0.06
     phương
    -0.06
     khởi
    -0.06
     Lit
    -0.06
     "=
    -0.06
    POSITIVE LOGITS
    ๆ
    0.07
    gsub
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
     speedy
    0.07
    No
    0.06
    	category
    0.06
     NES
    0.06
    opyright
    0.06
    Theo
    0.06
     －
    0.06
    Act Density 0.009%

    No Known Activations