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

    Neuronpedia

    INDEX
    Explanations

    no single answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.48
    ହା
    0.46
    t
    0.45
     spectacularly
    0.44
    ]+\
    0.43
    là
    0.42
    an
    0.42
    igui
    0.41
    hares
    0.41
    hale
    0.41
    POSITIVE LOGITS
    কুট
    0.50
     એક
    0.47
     ঝ
    0.47
     হাত
    0.47
     прис
    0.46
     이미지
    0.45
     pyramids
    0.45
     schedules
    0.45
     kingdoms
    0.45
     اک
    0.43
    Act Density 0.000%

    No Known Activations