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

    Neuronpedia

    INDEX
    Explanations

    Racing distances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unda
    -0.07
    ente
    -0.07
    advert
    -0.07
     rejects
    -0.07
     Connector
    -0.07
     dash
    -0.07
     compte
    -0.07
     region
    -0.06
    .func
    -0.06
     Để
    -0.06
    POSITIVE LOGITS
     intending
    0.07
    .assert
    0.06
    inger
    0.06
     vědom
    0.06
    "context
    0.06
    ]]=
    0.06
     біль
    0.06
     Kuala
    0.06
    Vectorizer
    0.06
     Additionally
    0.06
    Act Density 0.015%

    No Known Activations