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

    Neuronpedia

    INDEX
    Explanations

    research funding acknowledgment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sab
    -0.07
    lists
    -0.06
    .feedback
    -0.06
     Margaret
    -0.06
    เลข
    -0.06
     RCS
    -0.06
     traveled
    -0.06
    aviors
    -0.06
    .creator
    -0.06
    ,to
    -0.06
    POSITIVE LOGITS
     demek
    0.07
     Yine
    0.06
     kısm
    0.06
     đ
    0.06
    /goto
    0.06
     Parliamentary
    0.06
    __)↵↵↵
    0.06
     ipsum
    0.06
     "{"
    0.06
     EventHandler
    0.06
    Act Density 0.008%

    No Known Activations