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

    Neuronpedia

    INDEX
    Explanations

    ~~

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    стра
    -0.07
     Заг
    -0.07
    еком
    -0.06
     مربع
    -0.06
    458
    -0.06
     DIST
    -0.06
     극
    -0.06
     Patriot
    -0.06
    AIL
    -0.06
     ブ
    -0.06
    POSITIVE LOGITS
     characterized
    0.07
    ([$
    0.07
    categoria
    0.06
    Define
    0.06
    ocop
    0.06
    .Parser
    0.06
    .queue
    0.06
     Ridley
    0.06
     anz
    0.06
    How
    0.06
    Act Density 0.011%

    No Known Activations