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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ge
    -0.07
     večer
    -0.07
     rychle
    -0.07
     giáo
    -0.07
    istros
    -0.07
    ToDevice
    -0.06
    しまう
    -0.06
     hizo
    -0.06
    navigate
    -0.06
    ưa
    -0.06
    POSITIVE LOGITS
     Peripheral
    0.07
     homic
    0.06
    Consult
    0.06
    tester
    0.06
    ([\
    0.06
    -inf
    0.06
    يان
    0.06
    (docs
    0.06
     artificial
    0.06
    _follow
    0.06
    Act Density 0.003%

    No Known Activations