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

    Neuronpedia

    INDEX
    Explanations

    technical operations and file handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ার্ট
    0.48
    4
    0.48
     Capability
    0.47
    <h1>
    0.47
    Made
    0.46
    Unified
    0.46
    Mobil
    0.46
    Weeks
    0.46
     YEAR
    0.46
     Techniques
    0.46
    POSITIVE LOGITS
     slams
    0.52
    asmim
    0.50
     benches
    0.50
     cobert
    0.50
    íp
    0.47
     ciertas
    0.46
    acchati
    0.46
     окре
    0.46
     dificultades
    0.44
     somente
    0.44
    Act Density 0.001%

    No Known Activations