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

    Neuronpedia

    INDEX
    Explanations

    contrastive conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    0.84
     #
    0.80
     #{
    0.74
     cites
    0.73
     சாலை
    0.71
     KeyError
    0.67
     ­
    0.66
    #.
    0.66
    #{
    0.65
     #"
    0.65
    POSITIVE LOGITS
     Besides
    1.16
    Besides
    1.14
    Although
    1.11
    Even
    1.03
    They
    1.02
     Although
    1.00
    Seeing
    0.99
    He
    0.95
     Even
    0.93
    When
    0.93
    Act Density 0.000%

    No Known Activations