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

    Neuronpedia

    INDEX
    Explanations

    age ranges and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bail
    -0.07
    igham
    -0.07
    Long
    -0.07
     Maggie
    -0.07
    🍍
    -0.07
    G
    -0.07
     üzerinden
    -0.07
    andan
    -0.07
     sig
    -0.07
     tam
    -0.07
    POSITIVE LOGITS
    供图
    0.07
     Globals
    0.07
    uled
    0.07
     Extras
    0.07
     Circle
    0.07
    和完善
    0.06
    勇气
    0.06
    obody
    0.06
     [],
↵
    0.06
     plumbing
    0.06
    Act Density 0.003%

    No Known Activations