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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rcode
    -0.07
    ["_
    -0.07
     Algorithm
    -0.07
    アー
    -0.07
     منه
    -0.06
    ظمة
    -0.06
    .title
    -0.06
    हर
    -0.06
    طبي
    -0.06
     Ally
    -0.06
    POSITIVE LOGITS
     fruition
    0.07
    rowse
    0.07
    prefer
    0.06
     siguiente
    0.06
     jac
    0.06
     subjected
    0.06
     ridiculously
    0.06
     restriction
    0.06
     hugely
    0.06
     страш
    0.06
    Act Density 0.012%

    No Known Activations