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

    Neuronpedia

    INDEX
    Explanations

    URLs with path segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sogenannten
    0.49
     had
    0.39
    inni
    0.38
     rade
    0.38
     cosidd
    0.37
    적으로
    0.37
     sogenannte
    0.37
     nieco
    0.37
     saiu
    0.36
     believed
    0.35
    POSITIVE LOGITS
    cgi
    0.55
     सक्सेस
    0.40
    اؤ
    0.39
    🍲
    0.39
     फस
    0.36
    WebApp
    0.36
    apps
    0.36
    projects
    0.35
    repos
    0.35
    Facilities
    0.35
    Act Density 0.011%

    No Known Activations