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

    Neuronpedia

    INDEX
    Explanations

    ever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poucos
    0.40
     শতা
    0.37
    వచ్చు
    0.37
     এক্ষেত্রে
    0.35
    ][_
    0.35
    における
    0.35
    𝓗
    0.35
     الشيء
    0.35
     çeşitli
    0.34
     ہوں
    0.34
    POSITIVE LOGITS
     ever
    4.50
    ever
    3.56
     Ever
    3.55
     EVER
    3.53
    Ever
    3.44
    EVER
    3.13
     ooit
    2.75
     pernah
    2.19
     Everett
    2.08
     euer
    1.89
    Act Density 0.047%

    No Known Activations