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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (indent
    -0.07
     drainage
    -0.07
    κά
    -0.07
     besie
    -0.07
     cabins
    -0.07
     hơn
    -0.06
     tendon
    -0.06
    	ds
    -0.06
     lesen
    -0.06
    (Return
    -0.06
    POSITIVE LOGITS
    ={[
    0.07
     建
    0.07
     έ
    0.06
     作
    0.06
    SCII
    0.06
     Orta
    0.06
    .w
    0.06
    boot
    0.06
    �
    0.06
    EHICLE
    0.06
    Act Density 0.006%

    No Known Activations