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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     konu
    -0.07
     놓
    -0.07
    Kenn
    -0.06
     Н
    -0.06
     GETGLOBAL
    -0.06
    ]‏
    -0.06
    ']!='
    -0.06
     Philadelphia
    -0.06
    ЕН
    -0.06
     Bottom
    -0.06
    POSITIVE LOGITS
    _ser
    0.07
    .Iter
    0.06
     Sys
    0.06
    lica
    0.06
     телеф
    0.06
    -secondary
    0.06
    .Cons
    0.06
    _kind
    0.06
    。」
    0.06
     civic
    0.06
    Act Density 0.042%

    No Known Activations