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

    Neuronpedia

    INDEX
    Explanations

    newly created

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಗದ
    0.41
    Compressed
    0.39
    weighted
    0.38
    쨰
    0.35
     FabD
    0.34
    ͤ
    0.34
    uridad
    0.33
    πος
    0.33
    णातील
    0.33
    Weighted
    0.33
    POSITIVE LOGITS
     newly
    3.73
    Newly
    3.25
     Newly
    3.23
     freshly
    2.80
     recién
    2.80
     recently
    2.39
     সদ্য
    2.22
    recently
    2.06
     недавно
    2.02
     Recently
    1.96
    Act Density 0.044%

    No Known Activations