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

    Neuronpedia

    INDEX
    Explanations

    sua sponte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decom
    -0.07
    70
    -0.07
     CFL
    -0.06
     menos
    -0.06
    "f
    -0.06
    迷
    -0.06
    чим
    -0.06
    "A
    -0.06
    оглас
    -0.06
    ioc
    -0.06
    POSITIVE LOGITS
    _SYM
    0.08
     суспіль
    0.07
    บาท
    0.07
     linebacker
    0.07
    .constant
    0.07
     unrecognized
    0.06
     hole
    0.06
    quete
    0.06
     Viet
    0.06
    OptionPane
    0.06
    Act Density 0.001%

    No Known Activations