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

    Neuronpedia

    INDEX
    Explanations

    learn, established, cover, GitHub

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    తిక
    0.51
    eder
    0.49
     evapor
    0.48
    واد
    0.46
     Variations
    0.44
     derog
    0.44
     cauldron
    0.44
    ול
    0.43
    킷
    0.42
    ек
    0.42
    POSITIVE LOGITS
    nearby
    0.50
    nice
    0.48
    tm
    0.47
    wc
    0.47
    registered
    0.47
    infection
    0.47
    衛生
    0.47
    tourism
    0.46
    acje
    0.45
    datetime
    0.45
    Act Density 0.001%

    No Known Activations