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

    Neuronpedia

    INDEX
    Explanations

    health studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vielen
    -0.07
     Surf
    -0.07
     نیز
    -0.06
    ();↵↵↵
    -0.06
    ері
    -0.06
     Bucket
    -0.06
     inflated
    -0.06
     bumps
    -0.06
     máximo
    -0.06
    -earth
    -0.06
    POSITIVE LOGITS
    alborg
    0.07
     [@
    0.07
    (base
    0.06
    cert
    0.06
    ,:,:
    0.06
    .feedback
    0.06
    ):?>↵
    0.06
     عفش
    0.06
    astype
    0.06
    ,state
    0.06
    Act Density 0.035%

    No Known Activations