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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ![
    -0.07
     accumulated
    -0.07
     sandwiches
    -0.07
    Creating
    -0.06
     Sergeant
    -0.06
    maze
    -0.06
    Mas
    -0.06
    Chapter
    -0.06
    impl
    -0.06
     Consumers
    -0.06
    POSITIVE LOGITS
    .ticket
    0.07
    力量
    0.06
     MethodInvocation
    0.06
     Doll
    0.06
    ۱۹
    0.06
    टर
    0.06
    ‌اش
    0.06
     Replay
    0.06
    .isFile
    0.06
     councill
    0.06
    Act Density 0.001%

    No Known Activations