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
    Ol
    -0.06
    -like
    -0.06
     newX
    -0.06
    uela
    -0.06
    ЎыџN
    -0.06
    _Al
    -0.06
    _Ch
    -0.06
    	at
    -0.06
    .Linq
    -0.06
    Poor
    -0.06
    POSITIVE LOGITS
    ventions
    0.07
    riv
    0.07
    (image
    0.07
    alleries
    0.07
     stren
    0.06
     "|
    0.06
     ur
    0.06
    isbury
    0.06
     бенз
    0.06
    驶
    0.06
    Act Density 0.000%

    No Known Activations