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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avelength
    -0.07
    خراج
    -0.07
    tyard
    -0.06
    極
    -0.06
    STRUCTOR
    -0.06
    encies
    -0.06
     embroidery
    -0.06
    積
    -0.06
    _tools
    -0.06
     нек
    -0.06
    POSITIVE LOGITS
    替
    0.07
    	cf
    0.07
     Everything
    0.06
    システム
    0.06
    现场
    0.06
     potvr
    0.06
     fileType
    0.06
     Estado
    0.06
     행복
    0.06
     dads
    0.06
    Act Density 0.012%

    No Known Activations