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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resizable
    -0.07
    ==============
    -0.07
    nonnull
    -0.07
     dividing
    -0.06
     Channel
    -0.06
     nga
    -0.06
    θηκε
    -0.06
     Supports
    -0.06
     Chap
    -0.06
    함
    -0.06
    POSITIVE LOGITS
    '.$
    0.06
     목소
    0.06
     sing
    0.06
     happiness
    0.06
    inject
    0.06
    origin
    0.06
     법
    0.06
    官网
    0.06
    	Input
    0.06
    Ending
    0.06
    Act Density 0.000%

    No Known Activations