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

    Neuronpedia

    INDEX
    Explanations

    units of mass and definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zona
    0.43
     ブラック
    0.42
    ві
    0.41
     голо
    0.41
     ไม่มี
    0.40
    ディズニー
    0.40
    на
    0.40
    тип
    0.40
    ਕਾਰੀ
    0.40
     வளாக
    0.39
    POSITIVE LOGITS
     sele
    0.43
    ologis
    0.39
    parsers
    0.38
    ljed
    0.37
     ernst
    0.37
     City
    0.36
     TAR
    0.36
     area
    0.36
     backups
    0.36
    ubers
    0.36
    Act Density 0.005%

    No Known Activations