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

    Neuronpedia

    INDEX
    Explanations

    biological implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etrain
    0.46
    คุณภาพ
    0.44
     आढळ
    0.42
     সুন্দর
    0.41
     язы
    0.40
     erkannt
    0.38
    !')
    0.37
     евре
    0.37
    美しい
    0.37
    edy
    0.37
    POSITIVE LOGITS
     carpeta
    0.38
     deb
    0.36
     ማስ
    0.36
     Bridg
    0.36
     markers
    0.35
     simplest
    0.35
     specie
    0.34
     binders
    0.34
     abil
    0.34
    합
    0.34
    Act Density 0.000%

    No Known Activations