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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collaboration
    -0.07
    Rand
    -0.07
    :index
    -0.06
    HR
    -0.06
    练习
    -0.06
     row
    -0.06
    禁忌
    -0.06
    برش
    -0.06
    巡逻
    -0.06
    .setPositiveButton
    -0.06
    POSITIVE LOGITS
     וא
    0.07
    -sama
    0.07
    IDI
    0.07
    咪
    0.07
    爷
    0.07
    -chan
    0.07
     obsessed
    0.07
     vowels
    0.07
     demos
    0.07
    커
    0.07
    Act Density 0.002%

    No Known Activations