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

    Neuronpedia

    INDEX
    Explanations

    pronoun or continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     U
    0.49
     cul
    0.48
    closed
    0.46
     closed
    0.45
     US
    0.43
     Un
    0.43
    Cul
    0.43
     cun
    0.42
     Cul
    0.42
     Clement
    0.42
    POSITIVE LOGITS
    <unused88>
    0.39
    รัก
    0.38
    antz
    0.36
    యా
    0.36
     ints
    0.36
    NuGetPackage
    0.36
     অন্যত্র
    0.36
    Რ
    0.36
    abilités
    0.36
     dram
    0.36
    Act Density 0.000%

    No Known Activations