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

    Neuronpedia

    INDEX
    Explanations

    shapes and diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uste
    -0.06
    _instances
    -0.06
     Studi
    -0.06
     rés
    -0.06
     şi
    -0.06
     reject
    -0.06
     úč
    -0.06
    Suc
    -0.05
    袖
    -0.05
     buff
    -0.05
    POSITIVE LOGITS
     于
    0.07
    —one
    0.06
    loid
    0.06
    -clear
    0.06
     PLACE
    0.06
    —an
    0.06
    물을
    0.06
    /terms
    0.06
     '-';↵
    0.06
    ัตว
    0.06
    Act Density 0.045%

    No Known Activations