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

    Neuronpedia

    INDEX
    Explanations

    foot traffic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.52
    in
    1.37
    kten
    1.19
    kala
    1.14
    ە
    1.14
    gies
    1.12
    k
    1.09
    klar
    1.02
    들이
    1.01
     финансовых
    1.00
    POSITIVE LOGITS
    >
    1.18
    н
    0.99
     categor
    0.96
    <
    0.96
    見
    0.93
    )。
    0.91
     not
    0.91
    น
    0.90
    <0x84>
    0.87
    V
    0.87
    Act Density 0.004%

    No Known Activations