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

    Neuronpedia

    INDEX
    Explanations

    impeding or normalizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rn
    0.46
    ますが
    0.43
     ficando
    0.42
     competencia
    0.42
    الى
    0.42
     be
    0.41
     creando
    0.41
    elic
    0.41
     competitiveness
    0.40
     caveats
    0.40
    POSITIVE LOGITS
     يا
    0.47
    ﺢ
    0.44
     Flavor
    0.43
     शशि
    0.43
     homozygous
    0.43
     휘
    0.43
     അള
    0.42
     നേര
    0.42
    gage
    0.42
    Circ
    0.42
    Act Density 0.003%

    No Known Activations