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

    Neuronpedia

    INDEX
    Explanations

    lose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mirror
    -0.07
    Raw
    -0.06
    allenge
    -0.06
    allenges
    -0.06
    NSURLSession
    -0.06
    ारत
    -0.06
     очист
    -0.06
     亚洲
    -0.06
     Pros
    -0.06
     ISC
    -0.06
    POSITIVE LOGITS
    .addObserver
    0.07
     compos
    0.07
    би
    0.07
     меся
    0.07
    (adj
    0.07
    :T
    0.06
     DEC
    0.06
    提
    0.06
    (${
    0.06
    _rule
    0.06
    Act Density 0.116%

    No Known Activations