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

    Neuronpedia

    INDEX
    Explanations

    Forward rendering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ros
    0.40
     Rosemary
    0.40
     Sche
    0.39
     trois
    0.38
    node
    0.38
     Renal
    0.38
     drie
    0.37
    mono
    0.37
     balk
    0.36
     bhar
    0.36
    POSITIVE LOGITS
    owner
    0.47
    講師
    0.42
    サポート
    0.41
    負責
    0.41
    KHR
    0.39
    ﻄ
    0.39
     প্রতিনিধ
    0.38
     responsáveis
    0.38
     غلط
    0.38
    ⌞
    0.38
    Act Density 0.000%

    No Known Activations