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

    Neuronpedia

    INDEX
    Explanations

    Dex, DX, Prom, Prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ㅃ
    0.43
    λία
    0.41
     세율
    0.38
    חנו
    0.38
    暇
    0.38
    Ầ
    0.37
    kjhtml
    0.37
    ristmas
    0.36
    )}{\
    0.36
    जि
    0.35
    POSITIVE LOGITS
     Prom
    0.52
    Prom
    0.48
    prom
    0.46
     prom
    0.44
     PROM
    0.40
     circulation
    0.39
    Trả
    0.39
     Prompt
    0.39
     promotes
    0.37
     trom
    0.37
    Act Density 0.011%

    No Known Activations