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

    Neuronpedia

    INDEX
    Explanations

    an open

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻨ
    0.42
    перы
    0.41
     Assemblies
    0.41
    লায়
    0.41
     Pemb
    0.38
     FEST
    0.38
     LAKE
    0.38
     ۱۹
    0.38
     Astro
    0.37
    νας
    0.37
    POSITIVE LOGITS
    sar
    0.43
    bo
    0.41
    za
    0.41
    arch
    0.40
    ate
    0.38
    excellent
    0.38
    aec
    0.38
    junk
    0.37
    atisme
    0.37
    ार्
    0.37
    Act Density 0.001%

    No Known Activations