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

    Neuronpedia

    INDEX
    Explanations

    at a scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perempt
    0.28
     पार्टियों
    0.27
     यही
    0.25
     शिविर
    0.25
    うち
    0.25
     গী
    0.25
     puzzled
    0.25
     mismo
    0.25
    ونه
    0.25
     yönelik
    0.24
    POSITIVE LOGITS
     heart
    0.37
     scale
    0.35
     cuore
    0.32
     surface
    0.32
     essentially
    0.31
     granular
    0.29
     resolutions
    0.28
     elemental
    0.27
     corazón
    0.27
     skala
    0.26
    Act Density 0.027%

    No Known Activations