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

    Neuronpedia

    INDEX
    Explanations

    options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("")
    -0.07
     isbn
    -0.06
    ßer
    -0.06
    ahrungen
    -0.06
    GENCY
    -0.06
     пять
    -0.06
     Craft
    -0.06
    _counter
    -0.06
    .SimpleButton
    -0.06
     asteroid
    -0.06
    POSITIVE LOGITS
     InputDecoration
    0.06
    jspb
    0.06
    一种
    0.06
    TA
    0.06
     Bucc
    0.06
    امبر
    0.06
     pudd
    0.06
     skirt
    0.06
    ว
    0.06
    ools
    0.06
    Act Density 0.007%

    No Known Activations