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

    Neuronpedia

    INDEX
    Explanations

    closing syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வற்றை
    0.39
    해서
    0.39
     microtub
    0.38
     خفی
    0.36
     জীবা
    0.36
    桠
    0.36
    啮
    0.35
    해요
    0.34
     વાળ
    0.34
     leukocyte
    0.33
    POSITIVE LOGITS
     ancak
    0.39
     Prash
    0.38
     Martín
    0.37
     Abril
    0.36
     prépar
    0.35
    वासन
    0.35
     namun
    0.35
     abge
    0.35
     அதன்
    0.35
     Priya
    0.34
    Act Density 0.052%

    No Known Activations