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

    Neuronpedia

    INDEX
    Explanations

    about places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    产生了
    0.41
    ђе
    0.39
     клини
    0.39
     Ereign
    0.38
    程
    0.38
    劶
    0.38
    ρικ
    0.37
     besch
    0.37
    łączyć
    0.37
    ewnętr
    0.37
    POSITIVE LOGITS
    Town
    0.49
    Tea
    0.45
    Nem
    0.42
    Per
    0.40
    Words
    0.40
    IPAL
    0.38
    ๋า
    0.38
    World
    0.38
    Views
    0.38
    About
    0.37
    Act Density 0.000%

    No Known Activations