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

    Neuronpedia

    INDEX
    Explanations

    programming commands and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trench
    0.20
     pthread
    0.20
     diffus
    0.19
     ফলে
    0.19
    Chick
    0.19
     atteint
    0.19
     alle
    0.19
     tril
    0.19
     diffe
    0.19
    係る
    0.18
    POSITIVE LOGITS
    hotel
    0.18
     Restaurant
    0.17
     धमाल
    0.17
    ruk
    0.17
     }"
    0.17
    awaiter
    0.17
     teha
    0.17
    娜
    0.16
     tehdä
    0.16
    hedron
    0.16
    Act Density 0.158%

    No Known Activations