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

    Neuronpedia

    INDEX
    Explanations

    version specifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ברת
    0.36
     চাহ
    0.36
    莜
    0.36
     Cord
    0.36
    طاء
    0.36
    0.36
     يون
    0.35
    Harga
    0.35
    ༔
    0.35
     Louie
    0.35
    POSITIVE LOGITS
    ami
    0.40
     distance
    0.38
    licted
    0.37
     distances
    0.37
    distance
    0.36
     indis
    0.36
     lâ
    0.36
     div
    0.36
    нечно
    0.35
     wonderful
    0.35
    Act Density 0.002%

    No Known Activations