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

    Neuronpedia

    INDEX
    Explanations

    numbered list item 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    சென்னை
    0.65
    <unused1990>
    0.61
    <unused1943>
    0.55
     pendulum
    0.55
     ओपी
    0.55
     outdoor
    0.55
    <unused279>
    0.54
     nở
    0.54
     распоря
    0.54
    ारस
    0.53
    POSITIVE LOGITS
    °)
    1.13
    번
    1.10
    .<
    1.06
    °.
    1.04
    .//
    1.03
    \.
    1.02
    .:
    1.00
    nd
    0.99
    단계
    0.97
    .*/
    0.97
    Act Density 0.357%

    No Known Activations