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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	bt
    -0.07
    Kom
    -0.06
     freezer
    -0.06
     Rockefeller
    -0.06
    	num
    -0.06
    .Master
    -0.06
     gender
    -0.06
     Lisa
    -0.06
     Kaepernick
    -0.06
    ераль
    -0.06
    POSITIVE LOGITS
    _drive
    0.08
    代理
    0.07
    odic
    0.07
     Montreal
    0.07
    스는
    0.07
    /news
    0.07
    โต
    0.06
    _cats
    0.06
    enaire
    0.06
     theolog
    0.06
    Act Density 0.228%

    No Known Activations