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

    Neuronpedia

    INDEX
    Explanations

    sports competitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imit
    -0.09
     awe
    -0.08
    Iw
    -0.08
     трас
    -0.08
     dzięki
    -0.08
     hain
    -0.08
     dap
    -0.08
    AIS
    -0.08
     traversal
    -0.08
     inzwischen
    -0.08
    POSITIVE LOGITS
    (inputs
    0.08
     neemt
    0.07
     eviction
    0.07
     guests
    0.07
     ζη
    0.07
     먼저
    0.07
     miembros
    0.07
     проводится
    0.07
    ма
    0.07
    mosis
    0.07
    Act Density 0.008%

    No Known Activations