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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     omas
    -0.07
    置
    -0.06
    íses
    -0.06
     humiliating
    -0.06
    ाएग
    -0.06
    Unicode
    -0.06
    ReadOnly
    -0.06
    -proof
    -0.06
     Ž
    -0.06
    +"&
    -0.06
    POSITIVE LOGITS
     sockets
    0.07
    0.07
     named
    0.07
     tired
    0.07
    ですか
    0.06
    .cm
    0.06
     marzo
    0.06
     solo
    0.06
    Auto
    0.06
     Algeria
    0.06
    Act Density 0.001%

    No Known Activations