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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    掌
    -0.07
    refs
    -0.07
     руки
    -0.06
     Attack
    -0.06
    kf
    -0.06
     IRequest
    -0.06
     kterých
    -0.06
    世界
    -0.06
     XCT
    -0.06
    Levels
    -0.06
    POSITIVE LOGITS
     ventured
    0.06
    _CPP
    0.06
    uide
    0.06
    こ
    0.06
    ुश
    0.06
     ui
    0.06
     dopo
    0.06
     FAQ
    0.06
     carp
    0.06
    exter
    0.06
    Act Density 0.033%

    No Known Activations