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

    Neuronpedia

    INDEX
    Explanations

    channels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getTarget
    -0.07
     recep
    -0.07
    astics
    -0.07
    ограф
    -0.07
    교육
    -0.07
     Верхов
    -0.07
    _squared
    -0.07
     liquids
    -0.07
    đ
    -0.06
     fatt
    -0.06
    POSITIVE LOGITS
     channel
    0.07
     Shel
    0.07
    ilha
    0.06
     tidy
    0.06
    оку
    0.06
     unconstitutional
    0.06
     dahi
    0.06
     completionHandler
    0.06
     manual
    0.06
     imaginative
    0.06
    Act Density 0.001%

    No Known Activations