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

    Neuronpedia

    INDEX
    Explanations

    predicting the future is hard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appe
    0.56
     sticks
    0.55
     cumpr
    0.53
     abhis
    0.51
     возра
    0.50
     interesa
    0.49
     acorns
    0.49
    ')],
    0.48
    เคร
    0.47
    คาเดมี
    0.45
    POSITIVE LOGITS
    not
    0.56
    muy
    0.44
    yte
    0.42
    iciencia
    0.42
     ವೇ
    0.42
    ute
    0.41
    Creat
    0.41
    io
    0.40
    antes
    0.40
    Alert
    0.39
    Act Density 0.002%

    No Known Activations