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

    Neuronpedia

    INDEX
    Explanations

    getting data or objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🈯
    0.22
     }//
    0.22
    ivado
    0.21
    hyung
    0.21
     élytres
    0.20
    ছেলে
    0.20
    🙍
    0.20
    🐊
    0.20
    🍠
    0.20
    بيوتر
    0.20
    POSITIVE LOGITS
    ↵
    0.25
    在
    0.25
    न
    0.22
    For
    0.21
    की
    0.21
    BC
    0.20
    PF
    0.20
    CC
    0.19
    OL
    0.19
    P
    0.19
    Act Density 0.080%

    No Known Activations