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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    subset
    -0.07
     closure
    -0.07
    ffset
    -0.07
    rones
    -0.07
    Suppress
    -0.07
     terminates
    -0.07
    mostat
    -0.07
     reloading
    -0.07
    enting
    -0.07
     browser
    -0.07
    POSITIVE LOGITS
    飞行员
    0.07
    /File
    0.07
    Ethernet
    0.07
    芸
    0.07
    .mixin
    0.06
     cây
    0.06
    格會員
    0.06
    片
    0.06
    蝙
    0.06
     Vegetable
    0.06
    Act Density 0.046%

    No Known Activations