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

    Neuronpedia

    INDEX
    Explanations

    php code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அலுவ
    0.46
    FieldValue
    0.46
     किससे
    0.44
    箩
    0.44
    }}-\
    0.43
    ाये
    0.42
    OAuth
    0.42
    籮
    0.41
    트롤
    0.41
     कारणों
    0.41
    POSITIVE LOGITS
    é
    0.46
    is
    0.45
    ี
    0.44
    зи
    0.42
     neuf
    0.42
    ти
    0.41
    жие
    0.41
     parque
    0.41
     subsequent
    0.41
     generalize
    0.41
    Act Density 0.005%

    No Known Activations