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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hai
    -0.07
     ParseException
    -0.07
     Parsing
    -0.07
    368
    -0.07
     налог
    -0.07
     crore
    -0.07
    ười
    -0.07
    貝
    -0.07
     ps
    -0.06
    .agent
    -0.06
    POSITIVE LOGITS
    0.07
    او
    0.06
    tap
    0.06
     lubric
    0.06
    EVENT
    0.06
    ฐาน
    0.06
    angen
    0.06
    jectory
    0.06
     vit
    0.06
     handguns
    0.06
    Act Density 0.021%

    No Known Activations