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

    Neuronpedia

    INDEX
    Explanations

    neural network layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     premières
    0.52
    ید
    0.51
    spiritual
    0.50
    olphe
    0.49
    ascin
    0.49
     nuestras
    0.46
    ча
    0.46
     percaya
    0.46
     кушымта
    0.45
    dimensioni
    0.45
    POSITIVE LOGITS
     Group
    0.48
     Alb
    0.43
     banner
    0.41
    排序
    0.40
    ";
    0.40
    Group
    0.40
    ทั้งหมด
    0.40
     Guard
    0.39
    ".$
    0.39
     CL
    0.39
    Act Density 0.017%

    No Known Activations