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

    Neuronpedia

    INDEX
    Explanations

    conservation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     riding
    -0.08
     الأح
    -0.07
     体
    -0.07
     STATE
    -0.07
    YO
    -0.07
    Combined
    -0.07
    <List
    -0.07
    рия
    -0.07
     �
    -0.06
     labeled
    -0.06
    POSITIVE LOGITS
     سین
    0.07
    andatory
    0.07
    outers
    0.06
    dataTable
    0.06
     komplex
    0.06
     lin
    0.06
    	control
    0.06
    Ї
    0.06
     elektron
    0.05
    .:
    0.05
    Act Density 0.003%

    No Known Activations