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

    Neuronpedia

    INDEX
    Explanations

    in the world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prawo
    0.52
    )
    0.50
     fanfare
    0.49
    ב
    0.49
     ASSEM
    0.48
    Z
    0.47
     मजाक
    0.47
     disassembly
    0.47
    '
    0.47
     imz
    0.46
    POSITIVE LOGITS
    របស់យើង
    0.53
    <unused56>
    0.52
    <unused65>
    0.52
    jš
    0.52
    jší
    0.51
    <unused85>
    0.50
    ıştır
    0.50
    quin
    0.48
    rar
    0.48
    lined
    0.48
    Act Density 0.001%

    No Known Activations