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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     எளி
    0.45
     rechargeable
    0.45
     VRS
    0.44
     सुमारे
    0.43
     ﷺ
    0.43
     Voiture
    0.41
     grasses
    0.40
     VG
    0.40
     ounces
    0.40
     MDR
    0.39
    POSITIVE LOGITS
    ika
    0.45
     Erklärung
    0.39
     der
    0.38
    Tib
    0.38
    ish
    0.37
    ană
    0.37
     distort
    0.36
    ängt
    0.36
    ue
    0.36
    obus
    0.36
    Act Density 0.002%

    No Known Activations