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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pag
    -0.06
    倫
    -0.06
     reacting
    -0.06
    .FAIL
    -0.06
     Keith
    -0.06
     cognitive
    -0.06
    /MM
    -0.06
     accru
    -0.06
     ################
    -0.06
    _mem
    -0.06
    POSITIVE LOGITS
     rookies
    0.08
    .onView
    0.07
    ер
    0.06
    eters
    0.06
    remain
    0.06
     adjustments
    0.06
     advantage
    0.06
     Switzerland
    0.06
    Qty
    0.06
    kelas
    0.06
    Act Density 0.015%

    No Known Activations