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

    Neuronpedia

    INDEX
    Explanations

    and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     außerdem
    0.40
    또한
    0.39
     inoltre
    0.38
    挛
    0.38
     ഏക
    0.38
     ಅಲ್ಲ
    0.35
    Combine
    0.35
    ർഡ്
    0.34
     ஆவார்
    0.34
     بينما
    0.33
    POSITIVE LOGITS
    とその
    1.85
    及其
    1.76
     beserta
    1.23
     और
    0.80
     và
    0.80
     и
    0.80
     وما
    0.78
     και
    0.77
     आणि
    0.76
    和他
    0.74
    Act Density 0.038%

    No Known Activations