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

    Neuronpedia

    INDEX
    Explanations

    grammar/sentence structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toplum
    -0.07
     missions
    -0.07
     หม
    -0.07
     SHOW
    -0.07
     pantry
    -0.07
    북도
    -0.07
     shops
    -0.07
    арх
    -0.06
     Faces
    -0.06
     اعمال
    -0.06
    POSITIVE LOGITS
    Ubergraph
    0.07
    jis
    0.06
    (display
    0.06
     thereafter
    0.06
    ｭ
    0.06
    ivated
    0.06
     accidental
    0.06
     Norwich
    0.06
    enzyme
    0.06
    VMLINUX
    0.06
    Act Density 0.031%

    No Known Activations