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

    Neuronpedia

    INDEX
    Explanations

    technical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ่วม
    0.43
     संभव
    0.40
    검
    0.40
     stock
    0.40
     convolutional
    0.39
     destro
    0.39
     검
    0.39
     molding
    0.39
     conceivably
    0.39
    Hue
    0.38
    POSITIVE LOGITS
    🧔
    0.45
     शत्र
    0.41
     DialogInterface
    0.40
    .!
    0.37
    ୧
    0.37
     //@
    0.37
    ..!
    0.37
     മാത്രമേ
    0.36
    षण
    0.36
    ༎
    0.36
    Act Density 0.000%

    No Known Activations