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

    Neuronpedia

    INDEX
    Explanations

    first in order or sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     basic
    0.77
     Beginning
    0.76
    Beginning
    0.75
    basic
    0.72
    Basic
    0.72
    roots
    0.71
    ប្រ
    0.71
    基本的な
    0.71
     उत्साह
    0.70
    の中
    0.68
    POSITIVE LOGITS
     먼저
    2.85
     first
    2.77
    先に
    2.52
    first
    2.48
     zuerst
    2.47
     primero
    2.47
     FIRST
    2.32
     først
    2.32
    首先
    2.24
    First
    2.19
    Act Density 0.243%

    No Known Activations