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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (source
    -0.07
     hayal
    -0.07
     Rek
    -0.07
     digits
    -0.06
    '>↵
    -0.06
    说
    -0.06
     trưng
    -0.06
     expans
    -0.06
     rehears
    -0.06
    (category
    -0.06
    POSITIVE LOGITS
    	session
    0.06
    *dt
    0.06
     fabs
    0.06
    	cr
    0.06
    national
    0.06
    ©©
    0.06
    quil
    0.06
    IllegalArgumentException
    0.06
    December
    0.06
    」と
    0.06
    Act Density 0.009%

    No Known Activations