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

    Neuronpedia

    INDEX
    Explanations

    win

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bulk
    -0.07
     silly
    -0.06
    Criterion
    -0.06
     movie
    -0.06
    ναν
    -0.06
    кі
    -0.06
    　　　　　　　　　　　
    -0.06
    니
    -0.06
     Variant
    -0.06
     Robot
    -0.06
    POSITIVE LOGITS
    adena
    0.08
    really
    0.07
     zwei
    0.06
    PCS
    0.06
    UIApplicationDelegate
    0.06
    �
    0.06
    (seconds
    0.06
     propri
    0.06
     началь
    0.06
    ıyorum
    0.06
    Act Density 0.004%

    No Known Activations