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

    Neuronpedia

    INDEX
    Explanations

    organization and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺨ
    0.48
    又は
    0.43
     tribulations
    0.43
    なのです
    0.41
    থি
    0.41
    }{}
    0.40
     таком
    0.40
    草原
    0.40
     Brice
    0.40
    ﾖ
    0.40
    POSITIVE LOGITS
     पार्टी
    0.48
     항상
    0.48
    ittees
    0.46
     පැ
    0.45
    ctime
    0.44
    ime
    0.44
     پس
    0.43
     पूर्णा
    0.42
     hỗ
    0.42
    ahrung
    0.42
    Act Density 0.000%

    No Known Activations