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
     scalp
    -0.06
    Unit
    -0.06
     Routing
    -0.06
    bris
    -0.06
     شهید
    -0.06
    .ToolTip
    -0.06
     причины
    -0.06
    ANK
    -0.06
    ,...↵↵
    -0.06
    เฉพาะ
    -0.06
    POSITIVE LOGITS
    xde
    0.07
     killing
    0.07
    另一
    0.07
    ={{↵
    0.07
     process
    0.06
     jim
    0.06
    (OpCodes
    0.06
     biraz
    0.06
     account
    0.06
     sculpt
    0.06
    Act Density 0.023%

    No Known Activations