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

    Neuronpedia

    INDEX
    Explanations

    Malayalam and Bengali greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vapor
    1.30
     behavioral
    1.27
     extracurricular
    1.26
     Nevada
    1.25
     secluded
    1.25
     favorable
    1.25
     beige
    1.25
    کي
    1.24
     exhort
    1.23
     maneuvers
    1.23
    POSITIVE LOGITS
     ক
    1.25
     فى
    1.19
     প
    1.18
     ল
    1.14
     স
    1.12
     এ
    1.07
     এক
    1.05
     ট্র
    1.05
     র
    1.05
     ম
    1.04
    Act Density 0.007%

    No Known Activations