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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जरूरतों
    0.41
    ҹ
    0.39
    𝑛
    0.38
    .¹
    0.38
    пред
    0.37
     определить
    0.37
     അറിയി
    0.37
    .!
    0.37
     両
    0.36
     పేర్కొ
    0.36
    POSITIVE LOGITS
    :");
    0.65
     =",
    0.61
    :\
    0.59
    :",
    0.59
    :";
    0.54
    "):
    0.52
    =");
    0.50
    ")):
    0.50
     Ergebnis
    0.50
           
    0.49
    Act Density 0.035%

    No Known Activations