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

    Neuronpedia

    INDEX
    Explanations

    instructions below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yeah
    0.40
    eev
    0.38
     presumably
    0.37
    yeah
    0.36
    ちなみに
    0.34
    ことなく
    0.33
     nevo
    0.33
    closePath
    0.32
    Comparable
    0.31
    ライズ
    0.31
    POSITIVE LOGITS
     below
    2.77
    below
    2.42
     ниже
    2.34
    Below
    2.31
     Below
    2.27
    下面
    2.22
     abaixo
    2.22
     아래
    2.22
    下記
    2.19
    下面的
    2.17
    Act Density 0.065%

    No Known Activations