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

    Neuronpedia

    INDEX
    Explanations

    java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ammed
    -0.08
    ığ
    -0.07
    -H
    -0.07
    ắt
    -0.07
     comply
    -0.07
    丞
    -0.07
    -coordinate
    -0.07
     Counsel
    -0.07
    Hang
    -0.07
    hek
    -0.07
    POSITIVE LOGITS
    ,re
    0.07
     WATCH
    0.07
     conclus
    0.07
     neur
    0.07
    Implementation
    0.07
    ສ
    0.06
    商贸
    0.06
    вшис
    0.06
    /mail
    0.06
     Dark
    0.06
    Act Density 0.003%

    No Known Activations