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

    Neuronpedia

    INDEX
    Explanations

    early work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disampaikan
    0.38
     [{'
    0.38
    ρυ
    0.36
    Ee
    0.35
     _$_
    0.35
    戴
    0.35
    Ds
    0.35
     EDA
    0.35
     [{"
    0.34
    ጆ
    0.34
    POSITIVE LOGITS
    cooler
    0.45
    klik
    0.42
     คลิ
    0.41
    碼
    0.40
    fitting
    0.39
    bukkit
    0.39
    banking
    0.38
    Hashing
    0.38
    啷
    0.38
    ನ್ಸ್
    0.38
    Act Density 0.000%

    No Known Activations