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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     y
    -0.07
     w
    -0.07
     Steven
    -0.07
    Steven
    -0.07
     EAST
    -0.07
     puck
    -0.06
    	usage
    -0.06
    	TR
    -0.06
     beneath
    -0.06
    ProductName
    -0.06
    POSITIVE LOGITS
     INTERN
    0.07
    874
    0.07
    _BACK
    0.07
    .isActive
    0.06
     evento
    0.06
     خوان
    0.06
     interstate
    0.06
     نسبت
    0.06
    743
    0.06
    845
    0.06
    Act Density 0.000%

    No Known Activations