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

    Neuronpedia

    INDEX
    Explanations

    specific phrase or technical term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Landscape
    0.47
    Landscape
    0.46
     Landscapes
    0.44
     Utility
    0.42
    äll
    0.41
     Packaging
    0.40
     landscape
    0.40
    landscape
    0.40
    erei
    0.38
    噦
    0.38
    POSITIVE LOGITS
     glandes
    0.48
     populace
    0.46
    वते
    0.45
     Δεν
    0.44
    тере
    0.44
    یش
    0.44
     felonies
    0.43
     закона
    0.43
    াঃ
    0.43
    suffix
    0.43
    Act Density 0.003%

    No Known Activations