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

    Neuronpedia

    INDEX
    Explanations

    citation details or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    দের
    0.93
    ्च
    0.91
    ことができます
    0.89
     Gruy
    0.88
    窣
    0.87
    says
    0.87
    ologique
    0.86
    sentences
    0.85
    צוני
    0.83
    araham
    0.82
    POSITIVE LOGITS
    en
    1.10
    al
    0.91
    i
    0.91
    o
    0.78
     factored
    0.77
     trusted
    0.75
     ric
    0.74
     sull
    0.73
    back
    0.73
    u
    0.73
    Act Density 0.001%

    No Known Activations