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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ING
    -0.07
    PIN
    -0.07
     ткани
    -0.06
    ensors
    -0.06
     trí
    -0.06
    _ICON
    -0.06
     EA
    -0.06
    ICO
    -0.06
     Xu
    -0.06
    ,item
    -0.06
    POSITIVE LOGITS
     губер
    0.07
    /\
    0.07
    ?“
    0.07
    �
    0.07
    丶
    0.07
     Roz
    0.07
     Savings
    0.07
    .(
    0.06
     preached
    0.06
    =?,
    0.06
    Act Density 0.022%

    No Known Activations