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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stopped
    -0.07
    展
    -0.06
    Govern
    -0.06
    Plain
    -0.06
     formulario
    -0.06
     butterfly
    -0.06
    management
    -0.06
    (ERROR
    -0.06
    329
    -0.06
    星期
    -0.06
    POSITIVE LOGITS
     reperc
    0.07
     لت
    0.07
    ADX
    0.06
    řeh
    0.06
     především
    0.06
    !..
    0.06
    BOT
    0.06
     MU
    0.06
     lear
    0.06
    мець
    0.05
    Act Density 0.047%

    No Known Activations