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

    Neuronpedia

    INDEX
    Explanations

    Code scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    麻木
    -0.07
    Ȥ
    -0.07
     recounted
    -0.07
    MARY
    -0.07
    好运
    -0.07
    pcodes
    -0.07
     involves
    -0.07
     stops
    -0.07
     roads
    -0.06
     SUMMARY
    -0.06
    POSITIVE LOGITS
     Trade
    0.07
     solidity
    0.07
     karış
    0.07
    IAS
    0.06
    자동차
    0.06
     �
    0.06
    קיץ
    0.06
     ITE
    0.06
     banking
    0.06
    _my
    0.06
    Act Density 0.001%

    No Known Activations