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

    Neuronpedia

    INDEX
    Explanations

    logic puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大全
    -0.07
     Naming
    -0.07
    jící
    -0.07
    회
    -0.06
     moot
    -0.06
     masterpiece
    -0.06
     mại
    -0.06
    crement
    -0.06
    �y
    -0.06
    .cur
    -0.06
    POSITIVE LOGITS
     пон
    0.07
     how
    0.06
    	Transform
    0.06
     δυ
    0.06
    -error
    0.06
     없는
    0.06
    split
    0.06
    removeAttr
    0.06
    _ERRORS
    0.06
    CGPoint
    0.06
    Act Density 0.003%

    No Known Activations