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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toJSON
    -0.07
    膘
    -0.07
    	light
    -0.07
     cleaner
    -0.07
     thicker
    -0.07
    ])/
    -0.07
     years
    -0.07
    การออกแบบ
    -0.06
    	load
    -0.06
    (details
    -0.06
    POSITIVE LOGITS
    (album
    0.07
    或者说
    0.07
    .bed
    0.07
    _REC
    0.07
    .Admin
    0.06
    hack
    0.06
     ск
    0.06
    تعامل
    0.06
     fam
    0.06
    פרויק
    0.06
    Act Density 0.006%

    No Known Activations