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

    Neuronpedia

    INDEX
    Explanations

    optim as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    டுப
    0.40
     binaries
    0.38
    binary
    0.38
     binary
    0.38
     centuries
    0.37
    Maquina
    0.37
    ставляет
    0.36
     geometrical
    0.36
    二进制
    0.36
     suffice
    0.35
    POSITIVE LOGITS
     betroffen
    0.39
     Announcement
    0.38
     ಕೊ
    0.37
     kemarin
    0.37
    ANDO
    0.37
     mukaan
    0.37
    特別な
    0.36
    pecific
    0.36
    keygen
    0.36
     koa
    0.36
    Act Density 0.000%

    No Known Activations