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

    Neuronpedia

    INDEX
    Explanations

    customer MDM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    0.49
    ine
    0.45
     institution
    0.44
    च्या
    0.43
     bero
    0.43
     de
    0.42
    การ
    0.42
    পি
    0.42
     providers
    0.42
     skilled
    0.41
    POSITIVE LOGITS
    followlike
    0.54
     ආකාර
    0.51
    landı
    0.50
     hào
    0.46
    knight
    0.46
     gxf
    0.46
    analyze
    0.46
     patrón
    0.46
    cruise
    0.46
    磋
    0.46
    Act Density 0.000%

    No Known Activations