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

    Neuronpedia

    INDEX
    Explanations

    not very

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    1.52
    αν
    1.29
    AN
    1.06
    an
    1.01
    на
    1.01
    ر
    1.01
    in
    0.99
    います
    0.93
    ęcie
    0.93
    ant
    0.92
    POSITIVE LOGITS
    Во
    1.14
    З
    1.11
    Ο
    1.11
    korzyst
    1.10
     radiotherapy
    1.10
    Ве
    1.08
     geotechnical
    1.05
    ანა
    1.03
     homeopathy
    1.02
     façon
    1.02
    Act Density 0.001%

    No Known Activations