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

    Neuronpedia

    INDEX
    Explanations

    Fishbone diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    قیه
    0.58
    пление
    0.52
    ]^
    0.48
     صدیق
    0.47
     dietitian
    0.46
     tormented
    0.46
     человека
    0.46
    щиеся
    0.46
    то
    0.45
    щал
    0.45
    POSITIVE LOGITS
    l
    0.46
     NCA
    0.45
    ↵↵
    0.43
     obviously
    0.41
     Estate
    0.39
     믿
    0.39
     Promise
    0.38
     electoral
    0.38
     northward
    0.38
     onscreen
    0.38
    Act Density 0.002%

    No Known Activations