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

    Neuronpedia

    INDEX
    Explanations

    YNAB budget

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.59
    ling
    0.53
    bins
    0.52
    '
    0.51
    lafen
    0.50
     શરીર
    0.49
     Welles
    0.48
     مذہ
    0.47
    ulent
    0.46
    මණ
    0.46
    POSITIVE LOGITS
     aluminium
    0.59
    К
    0.59
    8
    0.58
     alumina
    0.57
    6
    0.57
    aluminum
    0.57
     алюми
    0.54
     aluminum
    0.53
    3
    0.52
    Э
    0.52
    Act Density 0.001%

    No Known Activations