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

    Neuronpedia

    INDEX
    Explanations

    legal errors being harmless

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    終わ
    -0.08
    虹
    -0.07
     temps
    -0.07
    ﰒ
    -0.07
    UpdatedAt
    -0.07
    .failure
    -0.07
     période
    -0.07
    iệu
    -0.06
     Emotional
    -0.06
    理想的
    -0.06
    POSITIVE LOGITS
     racer
    0.08
     sacr
    0.07
     dịch
    0.07
     размер
    0.07
    	menu
    0.07
     sector
    0.07
    INCLUDE
    0.06
    _note
    0.06
    series
    0.06
     ResponseEntity
    0.06
    Act Density 0.005%

    No Known Activations