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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Friedrich
    -0.08
    orte
    -0.07
     истор
    -0.07
     flatten
    -0.07
     derivative
    -0.07
    _First
    -0.06
     проф
    -0.06
     Juliet
    -0.06
     істор
    -0.06
    qrt
    -0.06
    POSITIVE LOGITS
     Can
    0.14
    Can
    0.13
    can
    0.12
    CAN
    0.11
     CAN
    0.11
     can
    0.10
    -can
    0.10
    (can
    0.09
    .Can
    0.09
     cans
    0.09
    Act Density 0.051%

    No Known Activations