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

    Neuronpedia

    INDEX
    Explanations

    Math calculations and sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    App
    -0.08
    Additionally
    -0.07
    'appr
    -0.07
    Ctor
    -0.07
    ုပ်
    -0.07
    _descr
    -0.07
     yếu
    -0.07
     عوامل
    -0.07
    ండ్
    -0.07
     preced
    -0.07
    POSITIVE LOGITS
     successive
    0.10
     progressively
    0.10
     increment
    0.10
     Increment
    0.09
     increments
    0.09
     점
    0.08
    마다
    0.08
     incremental
    0.08
    .increment
    0.08
     தொடர்ந்து
    0.08
    Act Density 0.050%

    No Known Activations