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

    Neuronpedia

    INDEX
    Explanations

    hey there greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ８
    0.51
    ྞ
    0.50
    絢
    0.49
    णारे
    0.48
    ന്ത്രാ
    0.48
    ﺓ
    0.48
    脅
    0.48
    科学家
    0.46
    .”[
    0.46
    Ꭽ
    0.46
    POSITIVE LOGITS
    o
    0.57
    et
    0.52
    e
    0.51
     e
    0.51
    ob
    0.49
     Ro
    0.49
    emer
    0.48
    ome
    0.48
     vital
    0.48
    0.48
    Act Density 0.001%

    No Known Activations