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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hva
    -0.07
    omin
    -0.07
    -pop
    -0.07
     Tune
    -0.07
    	be
    -0.07
    仗
    -0.07
    uling
    -0.07
    �
    -0.06
    uant
    -0.06
    levelname
    -0.06
    POSITIVE LOGITS
    )';↵
    0.07
     conditions
    0.07
    \",\
    0.07
    Specifier
    0.07
    /***
    0.07
    Nor
    0.06
     필요
    0.06
     бы
    0.06
    Demand
    0.06
     IOException
    0.06
    Act Density 0.000%

    No Known Activations