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

    Neuronpedia

    INDEX
    Explanations

    temporary files and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bhi
    0.51
     walang
    0.51
     just
    0.50
     לר
    0.49
     l
    0.48
     lediglich
    0.48
    elif
    0.48
     nothing
    0.47
     não
    0.47
    ą
    0.47
    POSITIVE LOGITS
    SaveChanges
    0.63
    ри
    0.62
    ុន
    0.59
     హైదర్
    0.57
     बनती
    0.57
    彻
    0.56
    𝚑
    0.56
    袜子
    0.55
     ج
    0.54
    рита
    0.54
    Act Density 0.007%

    No Known Activations