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

    Neuronpedia

    INDEX
    Explanations

    note taking and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ാവ
    0.42
     academic
    0.42
    论文
    0.40
     टीचिंग
    0.40
     बाबर
    0.40
     académica
    0.39
     ISSN
    0.39
    submissions
    0.38
    Ḥ
    0.38
    学术
    0.38
    POSITIVE LOGITS
     самого
    0.38
     by
    0.38
     editor
    0.37
    tag
    0.35
     syg
    0.34
     همان
    0.34
     tag
    0.33
     tam
    0.33
     leap
    0.32
     reinvent
    0.32
    Act Density 0.000%

    No Known Activations