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

    Neuronpedia

    INDEX
    Explanations

    awkward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ണ്ണം
    0.42
    Sustainable
    0.41
     দুষ্ট
    0.40
    Му
    0.39
    ivasena
    0.38
    องค์
    0.38
     могло
    0.38
     справед
    0.38
     соло
    0.37
    स्फोट
    0.37
    POSITIVE LOGITS
     mortg
    0.39
    ංග
    0.37
     examined
    0.36
     ample
    0.36
     ವ್ಯ
    0.36
    staking
    0.36
     cofactor
    0.36
     pum
    0.36
     jogging
    0.36
    row
    0.35
    Act Density 0.000%

    No Known Activations