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

    Neuronpedia

    INDEX
    Explanations

    horizontal and vertical lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piz
    -0.07
     criminal
    -0.07
     télé
    -0.07
     Universe
    -0.07
     paradise
    -0.07
     capability
    -0.07
    /kernel
    -0.07
     ਪ
    -0.07
    Nonce
    -0.07
     ні
    -0.07
    POSITIVE LOGITS
     Fle
    0.09
     opini
    0.08
     Slip
    0.08
     trio
    0.07
    -legged
    0.07
     hollow
    0.07
     finger
    0.07
     во
    0.07
     scrum
    0.07
    กลาง
    0.07
    Act Density 0.016%

    No Known Activations