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

    Neuronpedia

    INDEX
    Explanations

    code keywords and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     приве
    0.35
     Tuhan
    0.34
    แห่ง
    0.33
    regation
    0.33
    ikh
    0.32
    洺
    0.32
    गतान
    0.32
    rukh
    0.30
     छोटा
    0.30
    fledged
    0.30
    POSITIVE LOGITS
    msgSender
    0.44
    ia
    0.40
    MyHomePage
    0.39
    parentElement
    0.38
    rvGroup
    0.37
    जीर
    0.37
     राजे
    0.37
    на
    0.36
    tv
    0.36
    তীশ
    0.36
    Act Density 0.011%

    No Known Activations