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

    Neuronpedia

    INDEX
    Explanations

    Questions/uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    초
    -0.06
    魂
    -0.06
     vòng
    -0.06
     insanların
    -0.06
    ו�
    -0.06
     abandonment
    -0.06
     plane
    -0.06
     smoothed
    -0.06
    base
    -0.06
     lig
    -0.06
    POSITIVE LOGITS
    italic
    0.07
    NZ
    0.07
    Little
    0.07
    Startup
    0.06
    드로
    0.06
    fds
    0.06
     ใน
    0.06
     Represent
    0.06
     adoles
    0.06
    Lee
    0.06
    Act Density 0.138%

    No Known Activations