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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Orlando
    0.53
    Hugo
    0.45
     dares
    0.44
     Orlando
    0.42
     Hugo
    0.42
    лую
    0.40
    Oklahoma
    0.38
     थरूर
    0.38
     Heard
    0.38
    Л
    0.37
    POSITIVE LOGITS
     reson
    0.39
     Di
    0.38
     مورد
    0.37
    分泌
    0.37
     Sheng
    0.36
     secre
    0.36
     Commonwealth
    0.35
     Jas
    0.35
     ja
    0.35
     kec
    0.35
    Act Density 0.000%

    No Known Activations