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

    Neuronpedia

    INDEX
    Explanations

    One

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gods
    -0.07
    lemn
    -0.07
     Beans
    -0.06
    (cell
    -0.06
    BoxLayout
    -0.06
    (dr
    -0.06
    _hp
    -0.06
    уск
    -0.06
     چرخ
    -0.06
    ecycle
    -0.06
    POSITIVE LOGITS
    _sur
    0.07
     Mah
    0.07
    .BLUE
    0.06
    _dx
    0.06
     America
    0.06
    ./(
    0.06
     وان
    0.06
    '];?>"
    0.06
     promotions
    0.06
    	goto
    0.06
    Act Density 0.004%

    No Known Activations