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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pathfinder
    -0.07
     Kosovo
    -0.07
     Ir
    -0.06
     Beispiel
    -0.06
    .Serialization
    -0.06
    �
    -0.06
    /modules
    -0.06
    ("/
    -0.06
     working
    -0.06
     человек
    -0.06
    POSITIVE LOGITS
     lớp
    0.07
    ва
    0.07
    nia
    0.06
    �
    0.06
    law
    0.06
    .“↵↵
    0.06
    átka
    0.06
    Ac
    0.06
    :(
    0.06
     slug
    0.06
    Act Density 0.002%

    No Known Activations