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

    Neuronpedia

    INDEX
    Explanations

    URLs and code links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $$$
    0.29
    local
    0.27
     tips
    0.27
     local
    0.27
    irk
    0.26
    Р
    0.26
     agency
    0.26
    luc
    0.26
     chuẩn
    0.26
     doce
    0.26
    POSITIVE LOGITS
    辘
    0.32
    寅
    0.31
    팠
    0.29
    빴
    0.28
    等多
    0.27
    ）；
    0.27
    cellaneous
    0.26
    惡
    0.26
    शोर
    0.26
    %；
    0.26
    Act Density 0.004%

    No Known Activations