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

    Neuronpedia

    INDEX
    Explanations

    writing to file or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     potrzeb
    0.46
     algoritmo
    0.46
     kanggo
    0.44
     construido
    0.42
     algorithms
    0.42
     costruito
    0.41
     funktioniert
    0.41
     algorit
    0.41
     jaoks
    0.41
     एग्जाम
    0.41
    POSITIVE LOGITS
     specified
    0.48
     指定
    0.43
    指定的
    0.43
    指定
    0.42
     మేరకు
    0.39
     twice
    0.38
    ไทย
    0.38
     GAAP
    0.37
    并
    0.37
     ไทย
    0.37
    Act Density 0.249%

    No Known Activations