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

    Neuronpedia

    INDEX
    Explanations

    65537; common goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ುವುದ
    0.42
     Finish
    0.41
     последу
    0.40
    finish
    0.40
     مکان
    0.40
     ellipses
    0.39
    >>)
    0.39
     forgive
    0.37
    .!
    0.37
     myself
    0.37
    POSITIVE LOGITS
    Qua
    0.39
    floxacin
    0.38
    埗
    0.38
    reshold
    0.38
    อด
    0.38
     <!--
    0.37
    मार
    0.37
    ရှ
    0.36
    nji
    0.36
    swürdig
    0.36
    Act Density 0.001%

    No Known Activations