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

    Neuronpedia

    INDEX
    Explanations

    only provide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。。
    1.36
    。」
    1.35
     πολύ
    1.31
     Ngoài
    1.25
     INSTIT
    1.23
    juje
    1.22
     Böyle
    1.22
     allah
    1.22
    .»
    1.19
     χωρίς
    1.19
    POSITIVE LOGITS
    eer
    1.20
    ipient
    1.14
    рб
    1.11
    oxic
    1.04
    द्दल
    1.01
     შემ
    1.00
    ivism
    0.98
    loved
    0.96
    ography
    0.95
    eers
    0.95
    Act Density 0.000%

    No Known Activations