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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (begin
    -0.07
    endez
    -0.07
    =NULL
    -0.07
     prediction
    -0.07
    店铺
    -0.06
    =en
    -0.06
    (be
    -0.06
    比如
    -0.06
    anned
    -0.06
    (Base
    -0.06
    POSITIVE LOGITS
    Oak
    0.07
    öğretim
    0.07
    _RAM
    0.07
    _false
    0.07
     hormones
    0.07
    タイム
    0.07
     esports
    0.07
     cans
    0.07
    Hooks
    0.07
    Statics
    0.07
    Act Density 0.010%

    No Known Activations