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

    Neuronpedia

    INDEX
    Explanations

    File

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    珍
    -0.07
     allergic
    -0.07
    azo
    -0.06
    емо
    -0.06
     امید
    -0.06
    润
    -0.06
     Xamarin
    -0.06
    Desk
    -0.06
    contrast
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Knowing
    0.07
     pissed
    0.07
     raining
    0.07
    LANG
    0.06
    OKIE
    0.06
     `"
    0.06
    .DAO
    0.06
     conflicting
    0.06
     Sa
    0.06
    빈
    0.06
    Act Density 0.004%

    No Known Activations