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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     servi
    -0.07
    iami
    -0.07
     международ
    -0.06
    _staff
    -0.06
     weight
    -0.06
     Stewart
    -0.06
     Behavior
    -0.06
     Prozent
    -0.06
    SQLException
    -0.06
     Fun
    -0.06
    POSITIVE LOGITS
    CKET
    0.06
     Π
    0.06
     BufferedReader
    0.06
     웹
    0.05
    criptors
    0.05
     ناب
    0.05
    .opens
    0.05
    Make
    0.05
     está
    0.05
     INIT
    0.05
    Act Density 0.007%

    No Known Activations