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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paddingBottom
    -0.07
     представ
    -0.07
     venture
    -0.07
     valueForKey
    -0.07
     ire
    -0.07
    anker
    -0.06
     karde
    -0.06
     zer
    -0.06
     possibilit
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     adjustment
    0.08
     setIs
    0.07
     Update
    0.07
     régl
    0.07
    Duplicate
    0.07
    בוצע
    0.07
    炅
    0.07
    👀
    0.07
    _RF
    0.07
     failing
    0.07
    Act Density 0.043%

    No Known Activations