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

    Neuronpedia

    INDEX
    Explanations

    how do i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.46
    ン
    0.42
     viciss
    0.42
    FUNCTION
    0.42
     deftly
    0.41
     tale
    0.41
    нове
    0.41
     बखूबी
    0.41
    лек
    0.41
     بسیار
    0.40
    POSITIVE LOGITS
     मुझे
    0.59
     puedo
    0.59
     myself
    0.54
     mogę
    0.52
     আমার
    0.50
     میرے
    0.50
    我可以
    0.49
     Pued
    0.49
    मुझे
    0.48
     tôi
    0.48
    Act Density 0.073%

    No Known Activations