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

    Neuronpedia

    INDEX
    Explanations

    webpage titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ahydro
    0.39
    ington
    0.37
    యే
    0.37
    leve
    0.36
    Hydrochloride
    0.36
    攣
    0.35
    膚
    0.34
    iberg
    0.33
    鹽
    0.32
     transvers
    0.32
    POSITIVE LOGITS
     Untitled
    0.63
     MyApp
    0.60
     untitled
    0.59
    我的
    0.58
    untitled
    0.58
    MyApp
    0.55
     我的
    0.55
     my
    0.54
     мой
    0.52
    myapp
    0.52
    Act Density 0.008%

    No Known Activations