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

    Neuronpedia

    INDEX
    Explanations

    developers, global, fat, free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manchas
    0.45
     juga
    0.45
     spongy
    0.45
     ټینس
    0.44
     crop
    0.44
     veer
    0.43
     buds
    0.43
     spy
    0.42
     zircon
    0.41
     handyman
    0.41
    POSITIVE LOGITS
    ৌ
    0.49
    hattam
    0.45
    >>(
    0.44
     되었
    0.43
     internationalen
    0.43
    errorhandler
    0.43
    tcpHeader
    0.42
    uania
    0.42
    없는
    0.42
     furent
    0.41
    Act Density 0.003%

    No Known Activations