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

    Neuronpedia

    INDEX
    Explanations

    period punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    하는데
    -0.07
    ług
    -0.07
    welcome
    -0.06
     throwable
    -0.06
     повед
    -0.06
     demasi
    -0.06
     doGet
    -0.06
    @student
    -0.06
     ([[
    -0.06
     meisten
    -0.06
    POSITIVE LOGITS
    King
    0.07
    itled
    0.06
     Mining
    0.06
     Executive
    0.06
    iling
    0.06
    Assertion
    0.06
     Edition
    0.06
    ltr
    0.06
    Instr
    0.06
    	global
    0.06
    Act Density 0.000%

    No Known Activations