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

    Neuronpedia

    INDEX
    Explanations

    influencing public opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    寻
    -0.06
    racak
    -0.06
    lifting
    -0.06
     nostalg
    -0.06
     trap
    -0.06
     Да
    -0.06
    Merge
    -0.06
    dge
    -0.06
    厅
    -0.06
    Allocation
    -0.06
    POSITIVE LOGITS
    (.
    0.08
     TextStyle
    0.07
     클래스
    0.07
     overs
    0.07
     onCreate
    0.07
     reducers
    0.07
     ACT
    0.07
    	ST
    0.06
    	alpha
    0.06
     tweets
    0.06
    Act Density 0.025%

    No Known Activations