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

    Neuronpedia

    INDEX
    Explanations

    quality and deals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unary
    0.41
     untenable
    0.39
     unwillingness
    0.38
     perturbation
    0.38
     fragmentary
    0.37
     repug
    0.37
     culp
    0.37
     assail
    0.37
     irradiated
    0.36
     grammatical
    0.36
    POSITIVE LOGITS
     Terbaik
    0.61
     terbaik
    0.51
     kaufen
    0.51
     baratos
    0.49
     Terbaru
    0.48
     Philippines
    0.48
     лучшие
    0.47
     kopen
    0.46
     мыкты
    0.46
     terbaru
    0.46
    Act Density 0.188%

    No Known Activations