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

    Neuronpedia

    INDEX
    Explanations

    reach out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     العد
    0.67
    TestingModule
    0.61
    물을
    0.61
    识别
    0.59
     erkennen
    0.59
    ्राष्ट
    0.58
     ಮಾತನಾಡ
    0.58
     Upcoming
    0.58
     jederzeit
    0.58
    Ignoring
    0.58
    POSITIVE LOGITS
     voz
    0.68
    voice
    0.64
     voix
    0.64
    pop
    0.62
     torna
    0.62
     vét
    0.61
     Mobile
    0.60
    second
    0.60
    枨
    0.57
    Pop
    0.57
    Act Density 0.169%

    No Known Activations