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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    申
    -0.07
     Tru
    -0.06
     electronic
    -0.06
     forefront
    -0.06
    Fight
    -0.06
    Ymd
    -0.06
     Kaiser
    -0.06
    Blueprint
    -0.06
     Session
    -0.06
     unofficial
    -0.06
    POSITIVE LOGITS
    чины
    0.07
     sauce
    0.07
     jinak
    0.07
    _SOURCE
    0.06
     jur
    0.06
     �
    0.06
     użytk
    0.06
    출장안마
    0.06
    .Glide
    0.06
     дитини
    0.06
    Act Density 0.088%

    No Known Activations