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

    Neuronpedia

    INDEX
    Explanations

    reviews and product analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NAA
    1.16
    ोन
    1.07
    т
    1.04
    යට
    1.04
     comb
    1.02
    wa
    1.01
    ்த்த
    1.01
    ت
    0.99
    ArgsConstructor
    0.97
    wor
    0.97
    POSITIVE LOGITS
    nama
    1.27
    濱
    1.14
     skirts
    1.14
    ▬▬▬▬
    1.14
     upravo
    1.12
     edildi
    1.11
    AMENTO
    1.10
     aaya
    1.09
    您可以
    1.07
     tomto
    1.07
    Act Density 0.000%

    No Known Activations