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

    Neuronpedia

    INDEX
    Explanations

    Initializing/creating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เก
    -0.08
    性的
    -0.07
    AX
    -0.06
    .MATCH
    -0.06
    WithName
    -0.06
    cipher
    -0.06
     Sheldon
    -0.06
     AssemblyFileVersion
    -0.06
     会
    -0.06
    >User
    -0.06
    POSITIVE LOGITS
     senin
    0.07
    /month
    0.06
     Wien
    0.06
     sch
    0.06
    ceries
    0.06
    另
    0.06
    foon
    0.06
    sizlik
    0.06
     всё
    0.06
     Παν
    0.06
    Act Density 0.077%

    No Known Activations