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

    Neuronpedia

    INDEX
    Explanations

    Accuracy, precision, imbalanced datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    だい
    1.21
    प
    1.18
    Probably
    1.16
    tiff
    1.16
     probablement
    1.15
    pronged
    1.15
    आशा
    1.14
    ität
    1.12
     মৃত
    1.11
    åg
    1.11
    POSITIVE LOGITS
    an
    1.09
    agement
    1.05
    وتر
    1.04
    صه
    1.02
     Necess
    1.01
     ABD
    1.01
     Kuwait
    1.01
     Gasoline
    1.01
     arsen
    1.00
     AP
    1.00
    Act Density 0.001%

    No Known Activations