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

    Neuronpedia

    INDEX
    Explanations

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Moreover
    0.45
    ор
    0.41
    например
    0.41
     например
    0.40
    Therefore
    0.40
    อื่นๆ
    0.40
    Ago
    0.38
    \
    0.38
    ྱ
    0.38
    ≒
    0.37
    POSITIVE LOGITS
     ecco
    0.55
     Another
    0.48
     let
    0.48
     gotta
    0.48
     walang
    0.47
     we
    0.46
     bienvenidos
    0.46
     മതി
    0.46
     misión
    0.46
     nové
    0.45
    Act Density 0.022%

    No Known Activations