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

    Neuronpedia

    INDEX
    Explanations

    potentially avoid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     һәм
    0.20
     Но
    0.18
     ಹಾಗೂ
    0.18
     অথবা
    0.17
     sprites
    0.17
     صہی
    0.16
     isotherms
    0.16
     ("
    0.16
     或
    0.16
     কিংবা
    0.16
    POSITIVE LOGITS
     have
    0.20
    為
    0.19
     jedna
    0.19
    지
    0.19
    강
    0.19
    have
    0.19
    成为
    0.19
     tienen
    0.18
     obsahuje
    0.18
     berusaha
    0.18
    Act Density 3.163%

    No Known Activations