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

    Neuronpedia

    INDEX
    Explanations

    biological terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اسے
    0.47
    izz
    0.46
     SoaException
    0.46
     Increases
    0.45
    occhi
    0.45
     I
    0.44
     cost
    0.44
     புதிய
    0.43
     crear
    0.43
     Schemes
    0.42
    POSITIVE LOGITS
    ك
    0.56
    如
    0.51
    上帝
    0.50
    Hallo
    0.48
    к
    0.48
    這個
    0.48
    สวัสดี
    0.48
    Как
    0.47
    Ми
    0.47
    世
    0.47
    Act Density 0.000%

    No Known Activations