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

    Neuronpedia

    INDEX
    Explanations

    studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    苻
    -0.07
    -node
    -0.06
    למת
    -0.06
     fortune
    -0.06
    罢
    -0.06
    Beat
    -0.06
    公顷
    -0.06
     commentator
    -0.06
    Suite
    -0.06
    Friendly
    -0.06
    POSITIVE LOGITS
    tics
    0.07
    (content
    0.07
    意见建议
    0.07
    �택
    0.07
    relationships
    0.07
    装配
    0.07
    _sw
    0.06
     =[
    0.06
    dap
    0.06
    一直以来
    0.06
    Act Density 0.032%

    No Known Activations