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

    Neuronpedia

    INDEX
    Explanations

    check airline websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    1.27
     Gletscher
    1.17
     humble
    1.15
    "${
    1.08
    ">${
    1.05
     useful
    1.03
    ﮭ
    1.03
     หนู
    1.00
     hasattr
    0.99
     caveat
    0.98
    POSITIVE LOGITS
    郎
    1.30
     wspom
    1.29
     inicio
    1.26
     início
    1.25
     песен
    1.25
     premières
    1.21
    ફેદ
    1.20
    rx
    1.20
     joc
    1.17
     bên
    1.16
    Act Density 0.000%

    No Known Activations