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

    Neuronpedia

    INDEX
    Explanations

    indicating purpose or benefit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.58
    ל
    0.46
    י
    0.45
    OF
    0.42
    ﺭ
    0.42
    し
    0.42
    レ
    0.40
    ﻭ
    0.40
    are
    0.38
    の通販
    0.38
    POSITIVE LOGITS
    ๒
    0.52
    ២
    0.50
     🌱
    0.49
    ۩
    0.49
    😧
    0.48
     to
    0.47
     číslo
    0.47
    0.46
     de
    0.46
    ong
    0.46
    Act Density 0.047%

    No Known Activations