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

    Neuronpedia

    INDEX
    Explanations

    specific details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    及其
    -0.07
     hei
    -0.07
    river
    -0.06
     biçimde
    -0.06
     trả
    -0.06
    动物
    -0.06
    _tri
    -0.06
     inverse
    -0.06
     vanished
    -0.06
     tipped
    -0.06
    POSITIVE LOGITS
    also
    0.07
    /{{$
    0.07
     SolidColorBrush
    0.06
    (withDuration
    0.06
    .det
    0.06
    _ACC
    0.06
     ""){↵
    0.06
     Ezek
    0.06
    кової
    0.06
     ssh
    0.06
    Act Density 0.162%

    No Known Activations