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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clown
    -0.07
    ाण
    -0.06
     nuôi
    -0.06
    cce
    -0.06
     acı
    -0.06
     blot
    -0.06
    言った
    -0.06
    جد
    -0.06
     长
    -0.06
    _story
    -0.06
    POSITIVE LOGITS
    ")))↵
    0.07
    popup
    0.07
     specialist
    0.07
    Welcome
    0.06
    xc
    0.06
    *C
    0.06
    =======↵
    0.06
    Listener
    0.06
    Expense
    0.06
    水平
    0.06
    Act Density 0.081%

    No Known Activations