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

    Neuronpedia

    INDEX
    Explanations

    creating and defining programming elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     !=
    1.02
    doesn
    0.94
     ==
    0.91
     =\
    0.89
    (*
    0.88
    =\
    0.84
    !?
    0.84
    Given
    0.83
    ->"
    0.83
    .(*
    0.82
    POSITIVE LOGITS
     Materialien
    1.01
     Materials
    0.99
     órganos
    0.94
     Languages
    0.94
     órgãos
    0.92
     employers
    0.90
     Charger
    0.90
     Philosophie
    0.89
     alcune
    0.89
     your
    0.89
    Act Density 0.073%

    No Known Activations