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

    Neuronpedia

    INDEX
    Explanations

    steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    块
    -0.07
     demonstrators
    -0.06
     중
    -0.06
    	work
    -0.06
     Например
    -0.06
    ewater
    -0.06
     downloads
    -0.06
     asoci
    -0.06
     feeds
    -0.06
    setValue
    -0.06
    POSITIVE LOGITS
    (&_
    0.06
     court
    0.06
    createElement
    0.06
    volution
    0.06
     Kushner
    0.06
    bff
    0.06
    -prepend
    0.06
     cara
    0.06
    _RSP
    0.06
    Nuitka
    0.06
    Act Density 0.012%

    No Known Activations