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

    Neuronpedia

    INDEX
    Explanations

    failure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ♯
    -0.08
     ideally
    -0.07
     summoned
    -0.07
     study
    -0.07
     advocates
    -0.07
    ʒ
    -0.07
    see
    -0.07
     topic
    -0.07
    <meta
    -0.07
     tea
    -0.06
    POSITIVE LOGITS
    기는
    0.08
     khách
    0.08
    垡
    0.07
    믄
    0.07
    لام
    0.07
     failed
    0.07
     manufactured
    0.07
     '">
    0.07
     Kn
    0.07
    传奇
    0.07
    Act Density 0.024%

    No Known Activations