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

    Neuronpedia

    INDEX
    Explanations

    Threading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    東京
    -0.06
     Girl
    -0.06
    出品
    -0.06
     blues
    -0.06
     мест
    -0.06
    soup
    -0.06
     한번
    -0.06
     perder
    -0.06
    ’ex
    -0.05
    =top
    -0.05
    POSITIVE LOGITS
     успеш
    0.07
    _delay
    0.07
     무슨
    0.07
    лося
    0.06
     trying
    0.06
    apy
    0.06
     �
    0.06
    まれ
    0.06
    ematic
    0.06
    JAVA
    0.06
    Act Density 0.009%

    No Known Activations