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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oir
    -0.07
    Published
    -0.07
    čení
    -0.07
    358
    -0.06
     Hen
    -0.06
     soils
    -0.06
    information
    -0.06
    idae
    -0.06
    径
    -0.06
    іч
    -0.06
    POSITIVE LOGITS
     codecs
    0.06
    .setState
    0.06
     dl
    0.06
     나는
    0.06
     Pension
    0.06
    rp
    0.06
     realtime
    0.06
     traverse
    0.06
     italic
    0.06
    Fitness
    0.06
    Act Density 0.008%

    No Known Activations