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

    Neuronpedia

    INDEX
    Explanations

    smallest to largest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ion
    0.52
    িন
    0.51
    Ж
    0.49
    exist
    0.48
    Ин
    0.48
    ческие
    0.47
     waren
    0.47
    Old
    0.46
    IOException
    0.46
    Iv
    0.46
    POSITIVE LOGITS
     modules
    0.49
     algorithms
    0.46
     זה
    0.46
     chatbots
    0.46
     tensorflow
    0.46
     Bezos
    0.46
     consoles
    0.45
    nections
    0.44
     Modules
    0.43
     codes
    0.43
    Act Density 0.002%

    No Known Activations