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

    Neuronpedia

    INDEX
    Explanations

    specific phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \}$,
    0.52
    ទី
    0.50
     bát
    0.50
     putative
    0.49
    "].
    0.48
    ENTE
    0.48
     باسکٹ
    0.48
    但在
    0.48
    }]$,
    0.47
    ອາຫານ
    0.47
    POSITIVE LOGITS
    as
    0.53
    eval
    0.49
    ad
    0.48
    m
    0.47
    imeters
    0.46
    ul
    0.46
    es
    0.45
    p
    0.45
    os
    0.44
    icaria
    0.44
    Act Density 0.001%

    No Known Activations