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

    Neuronpedia

    INDEX
    Explanations

    strict and explicit declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     luật
    0.52
     ferritin
    0.52
    瓠
    0.51
    Penis
    0.47
     ivvu
    0.47
     lysate
    0.46
     capilla
    0.46
    艨
    0.45
     pavattati
    0.45
     longitudine
    0.45
    POSITIVE LOGITS
    //
    0.49
     Global
    0.47
    namespace
    0.47
    ↵
    0.46
     global
    0.46
     Object
    0.46
    #
    0.46
    0.46
    0.45
    global
    0.45
    Act Density 0.001%

    No Known Activations