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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     객
    -0.07
    698
    -0.07
    MO
    -0.07
    BO
    -0.06
    _PHOTO
    -0.06
    џ
    -0.06
    łe
    -0.06
    	w
    -0.06
    mes
    -0.06
    鲜
    -0.06
    POSITIVE LOGITS
     coalition
    0.07
    esini
    0.06
     ник
    0.06
     describing
    0.06
     zvuky
    0.06
    itä
    0.06
     combines
    0.06
    izzard
    0.06
    <Category
    0.06
     feeds
    0.06
    Act Density 0.015%

    No Known Activations