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

    Neuronpedia

    INDEX
    Explanations

    -tree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uyền
    -0.07
     cages
    -0.07
    র
    -0.06
    decay
    -0.06
     Yelp
    -0.06
    "nil
    -0.06
    anlık
    -0.06
     녹
    -0.06
    .databind
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     ομάδα
    0.07
     都
    0.07
    jabi
    0.06
    Shortcut
    0.06
     rnn
    0.06
    angular
    0.06
     Taxes
    0.06
     Aspen
    0.06
     prost
    0.06
     /**↵
    0.06
    Act Density 0.000%

    No Known Activations