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

    Neuronpedia

    INDEX
    Explanations

    over time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    此同时
    0.54
    antemente
    0.47
     qualsiasi
    0.47
    χρι
    0.46
     maneras
    0.46
    transferases
    0.45
     সঙ্কট
    0.45
    dala
    0.45
    ا
    0.45
    zovaniyu
    0.44
    POSITIVE LOGITS
     across
    0.55
     over
    0.53
     years
    0.49
    Across
    0.46
     Across
    0.46
    Years
    0.46
     three
    0.45
    Over
    0.45
     span
    0.44
     mView
    0.42
    Act Density 0.063%

    No Known Activations