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

    Neuronpedia

    INDEX
    Explanations

    characteristics and scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Its
    1.04
     its
    1.01
    $.\
    0.98
    $.
    0.97
     ។
    0.96
    Its
    0.93
    ].
    0.90
     deren
    0.89
     an
    0.87
    $.}
    0.86
    POSITIVE LOGITS
     entirety
    1.20
     expanse
    1.17
     heyday
    0.99
     intricacies
    0.99
     extent
    0.96
     workings
    0.96
     totality
    0.91
     plethora
    0.88
     plight
    0.86
     brunt
    0.85
    Act Density 0.168%

    No Known Activations