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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    第五届
    -0.07
     Bá
    -0.07
    ⏃
    -0.07
    共青团
    -0.06
    绽放
    -0.06
     attacking
    -0.06
    Ne
    -0.06
    booking
    -0.06
    牵
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     inert
    0.07
     produto
    0.07
    erland
    0.07
    сп
    0.07
    價
    0.07
     IDE
    0.07
    <header
    0.07
     Horizontal
    0.06
    __$
    0.06
     INCIDENTAL
    0.06
    Act Density 0.004%

    No Known Activations