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

    Neuronpedia

    INDEX
    Explanations

    opening or approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ലെസ്
    1.29
    遵守
    1.23
     обра
    1.22
     laborales
    1.17
     borrar
    1.14
     将
    1.14
     maintien
    1.13
     қили
    1.13
    定律
    1.13
     ezzel
    1.12
    POSITIVE LOGITS
    s
    1.14
    glow
    1.10
    ে
    1.08
     ઉ
    1.08
    NE
    1.02
    ggi
    0.98
    guards
    0.96
     හා
    0.95
    ciation
    0.94
    iest
    0.93
    Act Density 0.000%

    No Known Activations