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

    Neuronpedia

    INDEX
    Explanations

    symbols and notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مارس
    -0.07
     unsus
    -0.06
    ächst
    -0.06
     xo
    -0.06
     đau
    -0.06
     полит
    -0.06
     scales
    -0.06
     Tep
    -0.06
    clud
    -0.06
     aras
    -0.06
    POSITIVE LOGITS
    根据
    0.07
    _gateway
    0.07
    271
    0.06
    sbin
    0.06
     latin
    0.06
     huy
    0.06
    465
    0.06
     employer
    0.06
     Admission
    0.06
     foregoing
    0.06
    Act Density 0.027%

    No Known Activations