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

    Neuronpedia

    INDEX
    Explanations

    overview

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndGet
    -0.07
    .getField
    -0.07
     distort
    -0.06
     �
    -0.06
    uments
    -0.06
    _pre
    -0.06
    HV
    -0.06
    edian
    -0.06
    -te
    -0.06
     cá
    -0.06
    POSITIVE LOGITS
     прид
    0.07
     recyclerView
    0.07
     дина
    0.07
    overview
    0.07
    ilog
    0.06
    민국
    0.06
     WHILE
    0.06
    ROL
    0.06
     dialogs
    0.06
    InnerText
    0.06
    Act Density 0.001%

    No Known Activations