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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xx
    -0.06
    -[
    -0.06
     NR
    -0.06
    蜜
    -0.06
    alist
    -0.06
     Destruction
    -0.06
    THE
    -0.06
    ắt
    -0.06
    ány
    -0.06
    HONE
    -0.06
    POSITIVE LOGITS
    ájem
    0.07
     яким
    0.07
     Hover
    0.06
    درس
    0.06
     heaps
    0.06
     titulo
    0.06
     lagi
    0.06
     должны
    0.06
     busc
    0.06
     Sequence
    0.06
    Act Density 0.001%

    No Known Activations