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

    Neuronpedia

    INDEX
    Explanations

    just-in-time compilation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     †
    -0.07
     initiation
    -0.07
     inşa
    -0.06
     probation
    -0.06
     waiting
    -0.06
    _context
    -0.06
     farm
    -0.06
     supervised
    -0.06
     noble
    -0.06
    Initialize
    -0.06
    POSITIVE LOGITS
    ."[
    0.07
     journée
    0.07
     ऑनल
    0.07
    TreeWidgetItem
    0.06
    иж
    0.06
    .unlock
    0.06
    ⌒
    0.06
    řím
    0.06
    vají
    0.06
     IPCC
    0.06
    Act Density 0.010%

    No Known Activations