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

    Neuronpedia

    INDEX
    Explanations

    Category

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (depend
    -0.06
    “But
    -0.06
    og
    -0.06
     unpack
    -0.06
     〉
    -0.06
     esper
    -0.06
     passages
    -0.06
     ψ
    -0.06
    thumb
    -0.06
     дит
    -0.06
    POSITIVE LOGITS
     Nodo
    0.07
    Jennifer
    0.06
    Mexico
    0.06
    illy
    0.06
    USART
    0.06
    cts
    0.06
    -category
    0.06
    KB
    0.06
    -operation
    0.06
    asından
    0.06
    Act Density 0.001%

    No Known Activations