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

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _semaphore
    -0.07
    ,nil
    -0.07
    imizeBox
    -0.06
     shark
    -0.06
     lässt
    -0.06
    мя
    -0.06
     Vũ
    -0.06
    dialogs
    -0.06
     predis
    -0.06
    ordon
    -0.06
    POSITIVE LOGITS
     Executive
    0.07
    .container
    0.06
    """.
    0.06
     م
    0.06
    vect
    0.06
     elevate
    0.06
     flipping
    0.06
     profoundly
    0.06
    요일
    0.06
     ภ
    0.06
    Act Density 0.012%

    No Known Activations