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

    Neuronpedia

    INDEX
    Explanations

    tors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrive
    -0.07
    PK
    -0.07
     Công
    -0.07
    Hub
    -0.07
    加载
    -0.07
     Validates
    -0.06
     capability
    -0.06
     scoff
    -0.06
     شب
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ドル
    0.08
    anders
    0.07
    сло
    0.07
     unfortunate
    0.07
    _changed
    0.07
    .getOrder
    0.06
     rtl
    0.06
     instructor
    0.06
    ло
    0.06
     &:
    0.06
    Act Density 0.002%

    No Known Activations