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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MaxValue
    -0.07
     kommer
    -0.06
    Cy
    -0.06
     sty
    -0.06
    _AV
    -0.06
    	message
    -0.06
    　ノ
    -0.06
    .pow
    -0.06
    GORITH
    -0.06
    /ms
    -0.06
    POSITIVE LOGITS
    ILLE
    0.06
     retard
    0.06
    -books
    0.06
     prematurely
    0.06
     neuen
    0.06
    forms
    0.06
    μιουργ
    0.06
     titten
    0.06
     из
    0.06
    BinContent
    0.06
    Act Density 0.000%

    No Known Activations