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

    Neuronpedia

    INDEX
    Explanations

    focus modes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pores
    0.40
     Laplace
    0.38
    точ
    0.38
    ofacial
    0.38
    バシー
    0.38
     rural
    0.37
     ماش
    0.37
     molar
    0.37
     मिश
    0.36
    লাগ
    0.36
    POSITIVE LOGITS
     verdens
    0.40
     dobr
    0.39
    য্
    0.39
     skapa
    0.39
    𝕥
    0.39
     prosecuted
    0.38
     industriales
    0.38
     Karo
    0.38
    Karo
    0.37
     tease
    0.37
    Act Density 0.002%

    No Known Activations