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

    Neuronpedia

    INDEX
    Explanations

    household statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -route
    -0.07
     خواه
    -0.07
     яй
    -0.07
    よね
    -0.07
     phen
    -0.07
    ียร
    -0.07
     DAY
    -0.06
     été
    -0.06
    prit
    -0.06
    олее
    -0.06
    POSITIVE LOGITS
    sembles
    0.07
    consum
    0.06
    leo
    0.06
    /engine
    0.06
    turn
    0.06
    Dragging
    0.06
    ющих
    0.06
     Doctors
    0.06
     LGBTQ
    0.06
    icago
    0.06
    Act Density 0.000%

    No Known Activations