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

    Neuronpedia

    INDEX
    Explanations

    carniv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twig
    -0.07
     shampoo
    -0.07
    nock
    -0.06
     sections
    -0.06
    bero
    -0.06
     policemen
    -0.06
    OCUS
    -0.06
    lat
    -0.06
     يك
    -0.06
    Jac
    -0.06
    POSITIVE LOGITS
     carniv
    0.11
     Carnival
    0.06
    )V
    0.06
     krb
    0.06
     черв
    0.06
    amanho
    0.06
    orders
    0.06
    .Validate
    0.06
     drinking
    0.06
    asive
    0.06
    Act Density 0.001%

    No Known Activations