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

    Neuronpedia

    INDEX
    Explanations

    hosting and moderation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flirt
    -0.07
     tunnel
    -0.07
    号
    -0.07
    Doug
    -0.07
     mData
    -0.07
     Civilization
    -0.07
     registration
    -0.07
    .subplots
    -0.07
    万吨
    -0.06
     frogs
    -0.06
    POSITIVE LOGITS
     volunte
    0.07
    덖
    0.07
    bol
    0.07
    جاب
    0.07
    局限
    0.06
    -how
    0.06
    二手车
    0.06
    =""↵
    0.06
     "",
    0.06
    UAGE
    0.06
    Act Density 0.035%

    No Known Activations