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

    Neuronpedia

    INDEX
    Explanations

    Program/organization descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moist
    -0.07
    רגש
    -0.07
    NM
    -0.07
    BUG
    -0.07
    nodeName
    -0.07
    看
    -0.07
    bounded
    -0.06
    CDF
    -0.06
    Level
    -0.06
    brown
    -0.06
    POSITIVE LOGITS
     confort
    0.07
    马桶
    0.07
    entionPolicy
    0.07
    领土
    0.06
     Frames
    0.06
     errorHandler
    0.06
    -enter
    0.06
    ӊ
    0.06
    cta
    0.06
     só
    0.06
    Act Density 0.184%

    No Known Activations