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

    Neuronpedia

    INDEX
    Explanations

    skeletons or Sans

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Neymar
    0.64
     Selena
    0.64
     proguardFiles
    0.64
    倭
    0.62
    MLA
    0.59
    junior
    0.59
     Pochettino
    0.59
    鲲
    0.59
    荸
    0.59
     Fukuoka
    0.57
    POSITIVE LOGITS
     Sans
    1.52
    Sans
    1.50
     sans
    1.45
    sans
    1.27
     skele
    1.13
     skeleton
    1.13
     Undert
    1.08
     skeletons
    1.05
    Skeleton
    0.98
    skeleton
    0.94
    Act Density 0.001%

    No Known Activations