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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     škola
    -0.07
    Weak
    -0.06
     aba
    -0.06
     коміс
    -0.06
    电脑
    -0.06
    .FileSystem
    -0.06
    heads
    -0.06
    Driving
    -0.06
     hanya
    -0.06
     الخاص
    -0.05
    POSITIVE LOGITS
    >');↵
    0.08
     racket
    0.08
     dram
    0.07
    ')])↵
    0.07
     mapView
    0.07
     leftist
    0.06
    큼
    0.06
    .unsubscribe
    0.06
     ])↵
    0.06
     neglected
    0.06
    Act Density 0.052%

    No Known Activations