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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mission
    -0.07
    olucion
    -0.07
     {:
    -0.06
    uild
    -0.06
     informational
    -0.06
    يم
    -0.06
     香港
    -0.06
     ());↵↵
    -0.06
    她们
    -0.05
    .INVISIBLE
    -0.05
    POSITIVE LOGITS
    elah
    0.08
    ı
    0.06
     chai
    0.06
     LaTeX
    0.06
    houses
    0.06
    ่ก
    0.06
    กลาง
    0.06
     لع
    0.06
     Anonymous
    0.06
    ργ
    0.06
    Act Density 0.113%

    No Known Activations