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

    Neuronpedia

    INDEX
    Explanations

    fewer less than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    範囲
    0.61
    範圍
    0.58
    ългария
    0.55
     quello
    0.55
    об
    0.53
     মান
    0.52
    䣼
    0.52
    更有
    0.52
     सुमन
    0.52
    适当
    0.52
    POSITIVE LOGITS
     than
    1.69
     niż
    1.21
     Than
    1.19
    than
    1.15
     THAN
    1.11
    Than
    1.05
     än
    1.00
     kuin
    0.88
     decât
    0.82
     ढाई
    0.80
    Act Density 0.038%

    No Known Activations