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

    Neuronpedia

    INDEX
    Explanations

    specific purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Enough
    0.81
     барои
    0.72
    for
    0.72
     для
    0.69
    Technology
    0.68
    Untuk
    0.67
    Algorithms
    0.67
     algoritmo
    0.67
     for
    0.67
     Enough
    0.66
    POSITIVE LOGITS
     purposes
    4.08
     Purposes
    3.24
     purpose
    2.76
     sake
    2.45
    purpose
    2.38
     Purpose
    2.21
    Purpose
    2.10
     целей
    1.96
    目的
    1.95
     PURPOSE
    1.88
    Act Density 0.427%

    No Known Activations