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

    Neuronpedia

    INDEX
    Explanations

    provide attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ப்பா
    0.42
     STORAGE
    0.40
     განს
    0.39
    Items
    0.39
     اق
    0.39
    BANG
    0.39
    senha
    0.38
    ဟာ
    0.38
     कॉम्
    0.38
    ITEMS
    0.38
    POSITIVE LOGITS
     attribution
    1.00
     attributing
    0.90
    attribution
    0.89
     Attribution
    0.88
     credited
    0.87
     credit
    0.85
     authorship
    0.80
     attributed
    0.79
     credits
    0.78
     Credit
    0.77
    Act Density 0.242%

    No Known Activations