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

    Neuronpedia

    INDEX
    Explanations

    programming code and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StarService
    0.39
    挛
    0.38
    λημα
    0.38
    编码
    0.37
     DATE
    0.37
    >;</
    0.37
     elegans
    0.36
    DateField
    0.36
    BuildActionEntry
    0.36
    DATE
    0.36
    POSITIVE LOGITS
    imbing
    0.48
     нерав
    0.43
     gauging
    0.39
    obut
    0.38
     cambios
    0.37
     climbing
    0.36
     ganas
    0.36
    umpulan
    0.36
     Cerc
    0.36
     Bez
    0.36
    Act Density 0.001%

    No Known Activations