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

    Neuronpedia

    INDEX
    Explanations

    uncommon words/terminology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ******
↵
    -0.07
    __':
↵
    -0.06
     ramps
    -0.06
    “They
    -0.06
    “This
    -0.06
                            
↵
    -0.06
    __
↵
    -0.06
     tours
    -0.06
    )),
↵
    -0.06
    

↵
    -0.06
    POSITIVE LOGITS
    عی
    0.06
     wol
    0.06
     equation
    0.06
     nơi
    0.06
     выход
    0.06
    ภาษ
    0.06
     searching
    0.06
     fø
    0.06
     centerX
    0.06
     PEOPLE
    0.06
    Act Density 0.428%

    No Known Activations