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

    Neuronpedia

    INDEX
    Explanations

    what to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑵
    1.26
    ВА
    1.24
    ᴊ
    1.23
    Wonderful
    1.20
    𝐑
    1.20
    κο
    1.20
    س
    1.18
    𝑫
    1.16
    𝑭
    1.15
    یو
    1.14
    POSITIVE LOGITS
    in
    1.10
    il
    1.09
    sized
    1.07
    ার
    1.04
     রকম
    1.04
    on
    1.02
    en
    1.02
    lukan
    0.99
    ación
    0.98
    ritten
    0.98
    Act Density 0.158%

    No Known Activations