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

    Neuronpedia

    INDEX
    Explanations

    dedicated to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ners
    -0.10
     Shade
    -0.09
    ienia
    -0.09
    oft
    -0.09
    hawks
    -0.09
    Tho
    -0.09
    clair
    -0.08
    uel
    -0.08
    leurs
    -0.08
    INGS
    -0.08
    POSITIVE LOGITS
    icated
    0.18
    ded
    0.18
    ly
    0.13
     Ded
    0.13
    DED
    0.13
     ded
    0.12
    -purpose
    0.12
     dedication
    0.12
    ately
    0.11
    icates
    0.11
    Act Density 0.021%

    No Known Activations