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

    Neuronpedia

    INDEX
    Explanations

    android permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tâ
    0.42
    分别是
    0.42
     específicos
    0.39
    Funding
    0.38
    Logger
    0.38
     OrderedDict
    0.38
    Ordinal
    0.37
    TextView
    0.36
     ущер
    0.36
     αι
    0.36
    POSITIVE LOGITS
     peripher
    0.40
     comm
    0.39
     sureties
    0.39
     Hewlett
    0.39
     प्रबंध
    0.38
    ρακ
    0.38
     herum
    0.38
     commiss
    0.38
     turpentine
    0.38
    ┉
    0.38
    Act Density 0.000%

    No Known Activations