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

    Neuronpedia

    INDEX
    Explanations

    difficulty with routines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لهذه
    0.39
     poteva
    0.39
     दिलच
    0.39
     passende
    0.39
     vhodné
    0.38
     ihre
    0.37
     engen
    0.37
     bilj
    0.37
     Beziehung
    0.36
     unknowingly
    0.36
    POSITIVE LOGITS
    ias
    0.45
    imientos
    0.41
    हालांकि
    0.41
    ys
    0.40
    kWh
    0.40
    피
    0.40
    (',
    0.39
    િમ
    0.39
    Another
    0.39
    as
    0.39
    Act Density 0.004%

    No Known Activations