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

    Neuronpedia

    INDEX
    Explanations

    data and business modeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     daisies
    0.41
     harvests
    0.41
     aDict
    0.40
    etlen
    0.38
    imetable
    0.37
     ét
    0.37
    ించిన
    0.37
     Zij
    0.36
    Ớ
    0.36
    ዳል
    0.35
    POSITIVE LOGITS
    modeling
    0.56
     modeling
    0.55
    Modeling
    0.55
     Models
    0.54
    <0xA1>
    0.54
    model
    0.54
    建模
    0.54
     Modeling
    0.53
     model
    0.51
     Modelling
    0.50
    Act Density 0.009%

    No Known Activations