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

    Neuronpedia

    INDEX
    Explanations

    what followed by statement or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    นาน
    0.38
    成本
    0.37
    <mask>
    0.36
    اتج
    0.36
    脩
    0.36
     FRE
    0.36
    购
    0.35
    叁
    0.35
    নান
    0.34
    Primo
    0.34
    POSITIVE LOGITS
    about
    0.48
     about
    0.46
     complicates
    0.45
    ak
    0.44
     вместо
    0.44
     instead
    0.43
     bunun
    0.40
     clinched
    0.40
     बजाय
    0.39
    ac
    0.39
    Act Density 0.006%

    No Known Activations