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

    Neuronpedia

    INDEX
    Explanations

    finding connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sterreich
    0.42
     படி
    0.39
    нинград
    0.39
    Все
    0.39
    BOOL
    0.38
    legraph
    0.37
    Limited
    0.37
    េរ
    0.37
    LIMITED
    0.37
     முக
    0.37
    POSITIVE LOGITS
     reg
    0.41
     jata
    0.40
     paprika
    0.39
     ink
    0.38
     These
    0.38
     these
    0.38
     CY
    0.38
     ör
    0.38
     ž
    0.38
     Davies
    0.38
    Act Density 0.005%

    No Known Activations