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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     터
    -0.10
     настолько
    -0.09
     상당
    -0.08
     Carp
    -0.08
     리
    -0.08
     福
    -0.08
     remarkably
    -0.08
     unusually
    -0.08
     Cycl
    -0.08
     Cic
    -0.08
    POSITIVE LOGITS
    Conclusion
    0.08
    productive
    0.08
    _index
    0.08
    Matches
    0.08
    Requirement
    0.08
    Contribution
    0.08
    _extent
    0.08
    Index
    0.08
     matches
    0.08
    صى
    0.08
    Act Density 0.038%

    No Known Activations