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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     substantial
    -0.06
     shouting
    -0.06
    ξει
    -0.06
    iens
    -0.05
    ЕР
    -0.05
    USR
    -0.05
    Russia
    -0.05
    _border
    -0.05
    ských
    -0.05
     Basket
    -0.05
    POSITIVE LOGITS
    trail
    0.07
    angstrom
    0.06
    //↵
    0.06
    ünde
    0.06
     gấp
    0.06
    Below
    0.06
     она
    0.06
    RFC
    0.06
    
    0.06
    _PED
    0.06
    Act Density 0.054%

    No Known Activations