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

    Neuronpedia

    INDEX
    Explanations

    bullet points/dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Green
    -0.08
    Green
    -0.08
     الس
    -0.07
     فر
    -0.07
     inspecting
    -0.07
    ODS
    -0.07
    134
    -0.07
    Land
    -0.07
     عليك
    -0.07
     jakie
    -0.07
    POSITIVE LOGITS
    很好
    0.09
     помогает
    0.09
     предлагает
    0.08
     Indicates
    0.08
    进行了
    0.08
    Allows
    0.08
     Indo
    0.08
     Allows
    0.08
     ample
    0.08
    .trans
    0.08
    Act Density 0.207%

    No Known Activations