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

    Neuronpedia

    INDEX
    Explanations

    View

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LAYER
    -0.07
     زمانی
    -0.06
     Workbook
    -0.06
     personals
    -0.06
    phalt
    -0.06
    _dst
    -0.06
    	Connection
    -0.06
     styl
    -0.06
    (ph
    -0.06
    <typename
    -0.06
    POSITIVE LOGITS
    immer
    0.07
    (server
    0.07
    eth
    0.07
    Coefficient
    0.07
     ＜
    0.07
     horn
    0.06
     may
    0.06
    もしれない
    0.06
    พอ
    0.06
    .valueOf
    0.06
    Act Density 0.001%

    No Known Activations