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

    Neuronpedia

    INDEX
    Explanations

    swing freely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sotheby
    0.52
     audiobook
    0.51
     Scottsdale
    0.48
     Finley
    0.48
     Trudeau
    0.46
     Walter
    0.46
     Wür
    0.45
     جوړونکي
    0.44
     Smithsonian
    0.44
     Rogers
    0.44
    POSITIVE LOGITS
     trains
    0.47
     said
    0.42
    _
    0.42
    Trains
    0.42
     hadrons
    0.40
     asserts
    0.39
    ày
    0.39
    And
    0.38
    Than
    0.38
     valves
    0.38
    Act Density 0.005%

    No Known Activations