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

    Neuronpedia

    INDEX
    Explanations

    size abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mCurrent
    -0.07
    Conversion
    -0.07
    -pop
    -0.06
     QSize
    -0.06
    -pad
    -0.06
     sometimes
    -0.06
     Ferdinand
    -0.06
    Dto
    -0.06
    	Port
    -0.06
    Ps
    -0.06
    POSITIVE LOGITS
    (blank
    0.07
     Pelosi
    0.07
     reliance
    0.06
     下午
    0.06
    ।
    0.06
    '=>
    0.06
    _SUFFIX
    0.06
    锁
    0.06
     facility
    0.06
    ="-
    0.06
    Act Density 0.003%

    No Known Activations