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

    Neuronpedia

    INDEX
    Explanations

    opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mirrors
    -0.07
     kuzey
    -0.06
    (round
    -0.06
     restless
    -0.06
     edged
    -0.06
    lic
    -0.06
    (argc
    -0.06
    conomy
    -0.06
    Answers
    -0.06
    фра
    -0.06
    POSITIVE LOGITS
    -%
    0.07
    CastException
    0.06
     Original
    0.06
     Сер
    0.06
     Neville
    0.06
    exampleModal
    0.06
     Fast
    0.06
     Ney
    0.06
    吹
    0.06
    \D
    0.06
    Act Density 0.028%

    No Known Activations