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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chords
    -0.07
    ecurity
    -0.07
    compat
    -0.07
     GNU
    -0.06
     بل
    -0.06
    	conf
    -0.06
    (work
    -0.06
     Subjects
    -0.06
    PART
    -0.06
    δες
    -0.06
    POSITIVE LOGITS
     gazet
    0.07
    Shortly
    0.07
    請
    0.06
     теат
    0.06
     Crunch
    0.06
     سریال
    0.06
     muối
    0.06
    GetPosition
    0.06
     kurum
    0.06
     ceny
    0.06
    Act Density 0.035%

    No Known Activations