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

    Neuronpedia

    INDEX
    Explanations

    explain, translate, or describe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laurels
    0.44
    the
    0.43
    約束
    0.43
    Promise
    0.42
     portal
    0.42
    Assume
    0.41
    Carry
    0.41
    portal
    0.41
    ForEach
    0.40
    finance
    0.40
    POSITIVE LOGITS
     비슷한
    0.46
    Apellido
    0.39
    עות
    0.39
     பங்க
    0.39
     इस्तेमाल
    0.38
     Hern
    0.38
    ᇂ
    0.38
     등으로
    0.38
     Flights
    0.38
    ೀನ
    0.38
    Act Density 2.199%

    No Known Activations