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

    Neuronpedia

    INDEX
    Explanations

    module

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Negative
    -0.07
    转向
    -0.07
     flex
    -0.07
    _RES
    -0.07
    .translate
    -0.06
     sj
    -0.06
     č
    -0.06
     susp
    -0.06
    .TextView
    -0.06
    日夜
    -0.06
    POSITIVE LOGITS
    InTheDocument
    0.08
    ynes
    0.08
    __,↵
    0.07
    伾
    0.07
     Inbox
    0.07
    กว
    0.07
     wandered
    0.07
     rubbish
    0.06
     dzieci
    0.06
     everywhere
    0.06
    Act Density 0.001%

    No Known Activations