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

    Neuronpedia

    INDEX
    Explanations

    Programming, instructions, machine learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    握手
    -0.07
    这只
    -0.07
    𝘐
    -0.07
    ద
    -0.07
     долл
    -0.06
    ASP
    -0.06
    昆山
    -0.06
    /options
    -0.06
     tossing
    -0.06
    ところ
    -0.06
    POSITIVE LOGITS
    疗
    0.08
     катал
    0.07
    ⤺
    0.07
     taxis
    0.07
     Matrix
    0.07
    blog
    0.07
    inputEmail
    0.07
     mast
    0.07
    𠳐
    0.07
     практи
    0.07
    Act Density 0.099%

    No Known Activations