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

    Neuronpedia

    INDEX
    Explanations

    political ideologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ída
    -0.07
     Carr
    -0.07
    arem
    -0.07
    बल
    -0.07
    ωνα
    -0.06
     progresses
    -0.06
     Workbook
    -0.06
    えない
    -0.06
    anie
    -0.06
    arket
    -0.06
    POSITIVE LOGITS
    etheus
    0.07
     Isis
    0.06
     suffer
    0.06
    getStyle
    0.06
    .Core
    0.06
     "{
    0.06
     исслед
    0.06
    onents
    0.06
    					↵					↵
    0.06
    	define
    0.06
    Act Density 0.063%

    No Known Activations