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

    Neuronpedia

    INDEX
    Explanations

    non

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minority
    -0.07
     puzzles
    -0.07
     mound
    -0.06
     Dwarf
    -0.06
    -0.06
     elementary
    -0.06
    角色
    -0.06
     revert
    -0.06
     pony
    -0.06
     residency
    -0.06
    POSITIVE LOGITS
     zig
    0.07
    .putText
    0.06
    heat
    0.06
    itag
    0.06
     handleError
    0.06
    �
    0.06
     >
↵
    0.06
     acı
    0.06
     Carol
    0.06
    oài
    0.06
    Act Density 0.001%

    No Known Activations