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
    Style
    -0.06
     Kons
    -0.06
    rees
    -0.06
     دین
    -0.06
    (balance
    -0.06
    osing
    -0.06
    Sketch
    -0.06
     Beds
    -0.06
    preset
    -0.06
    UND
    -0.06
    POSITIVE LOGITS
     crc
    0.06
     따라
    0.06
     advisor
    0.06
     giàu
    0.06
     कट
    0.06
    =admin
    0.06
     vibrant
    0.06
    -прав
    0.06
     Kanunu
    0.06
     FINAL
    0.06
    Act Density 0.004%

    No Known Activations