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

    Neuronpedia

    INDEX
    Explanations

    google ai gemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pepper
    0.43
     Panorama
    0.41
    Andrew
    0.40
     Pepper
    0.39
     кукуру
    0.38
     कराने
    0.37
    Roger
    0.37
     Sudbury
    0.37
     Andrew
    0.36
    وزر
    0.36
    POSITIVE LOGITS
    shim
    0.37
    RIB
    0.36
     Remix
    0.36
    RIBE
    0.36
    蒽
    0.35
    рим
    0.35
     Revised
    0.35
     kuba
    0.35
    IntVar
    0.34
    shin
    0.34
    Act Density 0.012%

    No Known Activations