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

    Neuronpedia

    INDEX
    Explanations

    HTML opening tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?=$
    1.32
    >
    1.29
     unbeatable
    1.23
     متحده
    1.23
    >`
    1.16
    >`,
    1.16
    艿
    1.14
     betterment
    1.12
     epitome
    1.12
    <?=
    1.12
    POSITIVE LOGITS
    ∑</
    1.16
    NF
    1.09
    freeze
    1.05
    ...</
    1.04
    NO
    1.03
    |</
    1.03
    com
    1.02
    Urban
    1.01
    Instant
    1.00
    েদ
    0.99
    Act Density 0.057%

    No Known Activations