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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ์โ
    -0.06
    Bounds
    -0.06
     Elvis
    -0.06
     NO
    -0.06
    yw
    -0.06
     peanuts
    -0.06
     [["
    -0.06
    ,self
    -0.06
     jo
    -0.06
     campos
    -0.06
    POSITIVE LOGITS
     information
    0.07
    019
    0.07
     readdir
    0.06
     productivity
    0.06
     کسب
    0.06
    /ap
    0.06
    _contact
    0.06
     refin
    0.06
    DataBase
    0.06
     debunk
    0.06
    Act Density 0.004%

    No Known Activations