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

    Neuronpedia

    INDEX
    Explanations

    code/math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     经
    -0.06
     cortex
    -0.06
    (Settings
    -0.06
    füh
    -0.06
    існо
    -0.06
    ::{
    -0.06
     가격
    -0.06
     发
    -0.06
     racer
    -0.06
    (uid
    -0.06
    POSITIVE LOGITS
    Creating
    0.06
     departed
    0.06
     convoy
    0.06
     dashes
    0.06
     OD
    0.06
     넣
    0.06
     thì
    0.06
    discount
    0.06
    Unlock
    0.06
     efficiencies
    0.06
    Act Density 0.202%

    No Known Activations