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

    Neuronpedia

    INDEX
    Explanations

    civilizations, industrials, onnx

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อ
    0.47
    یک
    0.45
     මෙ
    0.43
    値
    0.42
    VERTEX
    0.40
    Ik
    0.39
    isme
    0.38
    棟
    0.38
    So
    0.38
    ཾ
    0.38
    POSITIVE LOGITS
     archaeologist
    0.45
     clerg
    0.41
     philippines
    0.39
     armies
    0.38
     urn
    0.38
     romanos
    0.38
     archaeologists
    0.38
     foxes
    0.37
    ió
    0.37
     caves
    0.37
    Act Density 0.000%

    No Known Activations