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

    Neuronpedia

    INDEX
    Explanations

    recently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     descoper
    0.37
     लक्षण
    0.36
     descub
    0.33
    говор
    0.32
    гыз
    0.32
     sabores
    0.32
    ំពោះ
    0.32
     generaciones
    0.31
    わない
    0.31
     discovers
    0.31
    POSITIVE LOGITS
     two
    0.43
     april
    0.43
     April
    0.42
     February
    0.42
     recently
    0.41
     Asus
    0.40
     October
    0.40
     ASUS
    0.39
     shortly
    0.39
     لمدة
    0.39
    Act Density 0.002%

    No Known Activations