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

    Neuronpedia

    INDEX
    Explanations

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    가를
    0.22
    mice
    0.20
    ahi
    0.19
    нике
    0.19
     caball
    0.19
     legen
    0.19
    eine
    0.18
     einen
    0.18
    र्की
    0.18
    mans
    0.18
    POSITIVE LOGITS
     permeate
    0.23
     fontSize
    0.22
    𠃌
    0.22
     traversed
    0.22
     SizedBox
    0.21
    िफिशियल
    0.21
     imply
    0.21
    isVisible
    0.20
     Conversely
    0.20
     xa
    0.20
    Act Density 0.411%

    No Known Activations