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

    Neuronpedia

    INDEX
    Explanations

    fell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    扎
    -0.06
     наз
    -0.06
     trò
    -0.06
     Redskins
    -0.06
     IMF
    -0.06
    ajax
    -0.06
     샤
    -0.06
     हर
    -0.06
    -Man
    -0.06
    voor
    -0.06
    POSITIVE LOGITS
    持续
    0.06
    θεν
    0.06
    reck
    0.06
    qid
    0.06
     imagin
    0.06
     ف
    0.06
    んで
    0.06
     принимать
    0.06
     Sag
    0.06
    erness
    0.06
    Act Density 0.007%

    No Known Activations