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

    Neuronpedia

    INDEX
    Explanations

    family structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aviours
    -0.06
    ели
    -0.06
     STOCK
    -0.06
    ire
    -0.06
    pu
    -0.06
     bert
    -0.06
     Tobias
    -0.06
    wang
    -0.06
     tiến
    -0.06
    stm
    -0.06
    POSITIVE LOGITS
     dostup
    0.06
     الشركة
    0.06
    .readFile
    0.06
     stake
    0.06
    .Cursors
    0.06
     recognizes
    0.06
     franchises
    0.06
    alleries
    0.06
     getPassword
    0.06
     geile
    0.06
    Act Density 0.079%

    No Known Activations