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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    msgs
    -0.07
    cad
    -0.06
     Celebr
    -0.06
     //
    -0.06
    >`↵
    -0.06
    "});↵
    -0.06
     unidad
    -0.06
    ад
    -0.06
    ynam
    -0.06
     Sorting
    -0.06
    POSITIVE LOGITS
     hran
    0.07
     σχε
    0.07
     arasında
    0.07
     خدا
    0.07
     nạn
    0.06
    MERCHANTABILITY
    0.06
    visa
    0.06
    ArrayOf
    0.06
     WHILE
    0.06
     پا
    0.06
    Act Density 0.010%

    No Known Activations