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

    Neuronpedia

    INDEX
    Explanations

    Reading to the end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्पत
    -0.07
     evolves
    -0.06
    ########
    -0.06
    有限公司
    -0.06
    TestClass
    -0.06
     calloc
    -0.06
    actual
    -0.06
    enco
    -0.06
    也有
    -0.06
    calloc
    -0.06
    POSITIVE LOGITS
    attering
    0.08
    ESS
    0.07
    getter
    0.07
     dex
    0.06
    ortic
    0.06
    ovaná
    0.06
     cheat
    0.06
     buffers
    0.06
    atters
    0.06
     cocaine
    0.06
    Act Density 0.005%

    No Known Activations