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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⟷
    -0.07
    _SELECTED
    -0.07
    ᨯ
    -0.07
     Brexit
    -0.07
    ሞ
    -0.06
    本身就
    -0.06
     Fitzgerald
    -0.06
    URA
    -0.06
    IPA
    -0.06
    Woman
    -0.06
    POSITIVE LOGITS
    _learning
    0.07
    本钱
    0.07
     Association
    0.07
     MODULE
    0.07
    狐狸
    0.07
     Xml
    0.07
    awl
    0.07
     имя
    0.07
    饵
    0.07
    athe
    0.07
    Act Density 0.019%

    No Known Activations