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

    Neuronpedia

    INDEX
    Explanations

    consistency, agreement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mas
    -0.07
     MW
    -0.07
    Dal
    -0.07
     beginning
    -0.06
     Harlem
    -0.06
     rooms
    -0.06
     Lake
    -0.06
     bombed
    -0.06
    Trace
    -0.06
    sen
    -0.06
    POSITIVE LOGITS
    myfile
    0.08
     хви
    0.07
    情况
    0.07
    (formData
    0.06
     özg
    0.06
    .Mutex
    0.06
    ~~~~~~~~~~~~~~~~
    0.06
    κο
    0.06
     víde
    0.06
     sécurité
    0.06
    Act Density 0.008%

    No Known Activations