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

    Neuronpedia

    INDEX
    Explanations

    you must / will / need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NM
    0.42
     povinn
    0.41
    只好
    0.41
     مجبور
    0.40
    Deux
    0.39
     Pflicht
    0.39
     flickering
    0.38
    Utils
    0.38
     বোপ
    0.38
     가면
    0.38
    POSITIVE LOGITS
     spends
    0.62
     becomes
    0.49
     spend
    0.48
    Spend
    0.46
     earns
    0.45
     Spend
    0.45
     được
    0.44
     Daily
    0.43
    ళ
    0.42
    spend
    0.41
    Act Density 0.003%

    No Known Activations