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

    Neuronpedia

    INDEX
    Explanations

    naming scientific branch table files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стояние
    0.73
    Downloaded
    0.66
     Download
    0.66
    рость
    0.65
     హా
    0.64
     Cud
    0.64
     Matsuda
    0.63
     downloading
    0.62
     ओटी
    0.60
     Malaysia
    0.60
    POSITIVE LOGITS
     names
    2.40
     name
    2.33
     Names
    2.19
    name
    2.12
     Name
    2.06
    Name
    2.05
     nomes
    1.96
    Names
    1.93
     naming
    1.91
     nome
    1.90
    Act Density 0.930%

    No Known Activations