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

    Neuronpedia

    INDEX
    Explanations

    about your or their

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ရပ်
    0.48
     desktops
    0.48
    Melbourne
    0.46
    ጿ
    0.45
    ীষ
    0.45
    websites
    0.44
     mammals
    0.44
     resolutions
    0.42
    namespace
    0.42
    ບ
    0.42
    POSITIVE LOGITS
     袋
    0.50
    ilitar
    0.49
     消費
    0.49
     BCC
    0.47
     dick
    0.45
     kos
    0.44
     സി
    0.44
     annualized
    0.44
    uer
    0.44
     効果
    0.43
    Act Density 0.004%

    No Known Activations