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

    Neuronpedia

    INDEX
    Explanations

    SQL queries: SELECT, JOIN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dryden
    0.66
    на
    0.66
    ן
    0.65
    llis
    0.64
    ../
    0.63
    tanto
    0.63
     partea
    0.62
     chuột
    0.62
    ᱭ
    0.61
     espero
    0.60
    POSITIVE LOGITS
     Einstellung
    0.52
     Baths
    0.51
    ীর
    0.51
    c
    0.50
     그런데
    0.50
     Prinzip
    0.50
    式
    0.50
     Rolle
    0.49
     yıld
    0.49
    ح
    0.49
    Act Density 0.155%

    No Known Activations