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

    Neuronpedia

    INDEX
    Explanations

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lifetime
    -0.07
     Being
    -0.07
    outs
    -0.06
     increasing
    -0.06
     nhiều
    -0.06
     XX
    -0.06
     Bened
    -0.06
     fashionable
    -0.06
     Computer
    -0.06
    Lost
    -0.06
    POSITIVE LOGITS
     linking
    0.07
    ------↵↵
    0.07
    elpers
    0.07
    "fmt
    0.06
    、小
    0.06
    กร
    0.06
    ám
    0.06
    _default
    0.06
    voie
    0.06
     Chúa
    0.06
    Act Density 0.010%

    No Known Activations