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

    Neuronpedia

    INDEX
    Explanations

    money, inheritance, loans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    何か
    0.53
     keç
    0.49
    煕
    0.49
    ässä
    0.49
    assess
    0.48
    əm
    0.48
    有關
    0.48
    ဒ
    0.48
     Zelda
    0.47
    experiences
    0.47
    POSITIVE LOGITS
     Neue
    0.50
     되고
    0.47
    లతో
    0.46
    Pine
    0.43
    ي
    0.41
     Drei
    0.41
    rino
    0.40
    рино
    0.40
    ٣
    0.39
    يني
    0.38
    Act Density 0.000%

    No Known Activations