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

    Neuronpedia

    INDEX
    Explanations

    value for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    षेक
    0.44
    ٍ
    0.42
    otry
    0.41
    ተት
    0.41
    tható
    0.40
     ذلك
    0.39
    ством
    0.39
    ischen
    0.39
    ছুর
    0.39
    Boxing
    0.39
    POSITIVE LOGITS
    ראל
    0.48
     sleeping
    0.45
    дор
    0.44
     கந்த
    0.44
    CONTENTS
    0.44
     ἔ
    0.44
     Ski
    0.44
     FURN
    0.43
    珢
    0.43
     siè
    0.43
    Act Density 0.004%

    No Known Activations