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

    Neuronpedia

    INDEX
    Explanations

    Legal arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нал
    -0.07
     Mohammad
    -0.07
     Countries
    -0.06
     soo
    -0.06
    ✫
    -0.06
    材
    -0.06
    .bytes
    -0.06
    凉
    -0.06
    Storm
    -0.06
    coord
    -0.06
    POSITIVE LOGITS
    DropDown
    0.07
     treated
    0.07
    你看
    0.07
     classroom
    0.07
     Everyone
    0.07
    课堂教学
    0.06
    犋
    0.06
    过去
    0.06
    @Repository
    0.06
    .reporting
    0.06
    Act Density 0.003%

    No Known Activations